From d15fca53d299f78d4a8bc5eefeaa7c6866cb07a2 Mon Sep 17 00:00:00 2001 From: Double_V Date: Thu, 21 Jul 2022 09:55:42 +0800 Subject: [PATCH 01/14] Merge pull request #6824 from ChenNima/release/2.5-kie-save-res [kie]add write_kie_result to kie infer tool --- tools/infer_kie.py | 27 ++++++++++++++++++++++++++- 1 file changed, 26 insertions(+), 1 deletion(-) diff --git a/tools/infer_kie.py b/tools/infer_kie.py index 346e2e0aee..9375434cc8 100755 --- a/tools/infer_kie.py +++ b/tools/infer_kie.py @@ -88,6 +88,29 @@ def draw_kie_result(batch, node, idx_to_cls, count): cv2.imwrite(save_path, vis_img) logger.info("The Kie Image saved in {}".format(save_path)) +def write_kie_result(fout, node, data): + """ + Write infer result to output file, sorted by the predict label of each line. + The format keeps the same as the input with additional score attribute. + """ + import json + label = data['label'] + annotations = json.loads(label) + max_value, max_idx = paddle.max(node, -1), paddle.argmax(node, -1) + node_pred_label = max_idx.numpy().tolist() + node_pred_score = max_value.numpy().tolist() + res = [] + for i, label in enumerate(node_pred_label): + pred_score = '{:.2f}'.format(node_pred_score[i]) + pred_res = { + 'label': label, + 'transcription': annotations[i]['transcription'], + 'score': pred_score, + 'points': annotations[i]['points'], + } + res.append(pred_res) + res.sort(key=lambda x: x['label']) + fout.writelines([json.dumps(res, ensure_ascii=False) + '\n']) def main(): global_config = config['Global'] @@ -114,7 +137,7 @@ def main(): warmup_times = 0 count_t = [] - with open(save_res_path, "wb") as fout: + with open(save_res_path, "w") as fout: with open(config['Global']['infer_img'], "rb") as f: lines = f.readlines() for index, data_line in enumerate(lines): @@ -139,6 +162,8 @@ def main(): node = F.softmax(node, -1) count_t.append(time.time() - st) draw_kie_result(batch, node, idx_to_cls, index) + write_kie_result(fout, node, data) + fout.close() logger.info("success!") logger.info("It took {} s for predict {} images.".format( np.sum(count_t), len(count_t))) From 14e7e1185abd7c95aea94f5b534a36bb4033ec6b Mon Sep 17 00:00:00 2001 From: Evezerest <50011306+Evezerest@users.noreply.github.com> Date: Thu, 7 Jul 2022 10:33:50 +0800 Subject: [PATCH 02/14] Merge pull request #6677 from TonyJiangWJ/release/2.5 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit 修复内存泄露问题 --- .../java/com/baidu/paddle/lite/demo/ocr/OCRPredictorNative.java | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/deploy/android_demo/app/src/main/java/com/baidu/paddle/lite/demo/ocr/OCRPredictorNative.java b/deploy/android_demo/app/src/main/java/com/baidu/paddle/lite/demo/ocr/OCRPredictorNative.java index 622da2a3f9..41fa183dea 100644 --- a/deploy/android_demo/app/src/main/java/com/baidu/paddle/lite/demo/ocr/OCRPredictorNative.java +++ b/deploy/android_demo/app/src/main/java/com/baidu/paddle/lite/demo/ocr/OCRPredictorNative.java @@ -54,7 +54,7 @@ public class OCRPredictorNative { } public void destory() { - if (nativePointer > 0) { + if (nativePointer != 0) { release(nativePointer); nativePointer = 0; } From ec7ebd3625e905d401d71563a5b2137a744aadd2 Mon Sep 17 00:00:00 2001 From: shawn <1021362695@qq.com> Date: Fri, 24 Jun 2022 17:54:21 +0800 Subject: [PATCH 03/14] Update native.cpp (#6650) fix issue 6640 --- deploy/android_demo/app/src/main/cpp/native.cpp | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/deploy/android_demo/app/src/main/cpp/native.cpp b/deploy/android_demo/app/src/main/cpp/native.cpp index ced932556f..4961e5ecf1 100644 --- a/deploy/android_demo/app/src/main/cpp/native.cpp +++ b/deploy/android_demo/app/src/main/cpp/native.cpp @@ -47,7 +47,7 @@ str_to_cpu_mode(const std::string &cpu_mode) { std::string upper_key; std::transform(cpu_mode.cbegin(), cpu_mode.cend(), upper_key.begin(), ::toupper); - auto index = cpu_mode_map.find(upper_key); + auto index = cpu_mode_map.find(upper_key.c_str()); if (index == cpu_mode_map.end()) { LOGE("cpu_mode not found %s", upper_key.c_str()); return paddle::lite_api::LITE_POWER_HIGH; @@ -116,4 +116,4 @@ Java_com_baidu_paddle_lite_demo_ocr_OCRPredictorNative_release( ppredictor::OCR_PPredictor *ppredictor = (ppredictor::OCR_PPredictor *)java_pointer; delete ppredictor; -} \ No newline at end of file +} From 0560a138b2cd9d009ea1d0483402609f1b52a03b Mon Sep 17 00:00:00 2001 From: Double_V Date: Mon, 27 Jun 2022 09:08:16 +0800 Subject: [PATCH 04/14] Merge pull request #6625 from ynjang/ynjang update sorted_boxes --- tools/infer/predict_system.py | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/tools/infer/predict_system.py b/tools/infer/predict_system.py index 73b7155baa..3f322ecc6f 100755 --- a/tools/infer/predict_system.py +++ b/tools/infer/predict_system.py @@ -120,11 +120,14 @@ def sorted_boxes(dt_boxes): _boxes = list(sorted_boxes) for i in range(num_boxes - 1): - if abs(_boxes[i + 1][0][1] - _boxes[i][0][1]) < 10 and \ - (_boxes[i + 1][0][0] < _boxes[i][0][0]): - tmp = _boxes[i] - _boxes[i] = _boxes[i + 1] - _boxes[i + 1] = tmp + for j in range(i, 0, -1): + if abs(_boxes[j + 1][0][1] - _boxes[j][0][1]) < 10 and \ + (_boxes[j + 1][0][0] < _boxes[j][0][0]): + tmp = _boxes[j] + _boxes[j] = _boxes[j + 1] + _boxes[j + 1] = tmp + else: + break return _boxes From 5b195b85118717218a9c039459670888fe65860c Mon Sep 17 00:00:00 2001 From: paopjian <672034519@qq.com> Date: Thu, 16 Jun 2022 13:21:58 +0800 Subject: [PATCH 05/14] fix DeprecationWarning, (#6604) DeprecationWarning: The binary mode of fromstring is deprecated, as it behaves surprisingly on unicode inputs. Use frombuffer instead --- tools/infer/utility.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/infer/utility.py b/tools/infer/utility.py index 1eebc73f31..3d9bdee0ee 100644 --- a/tools/infer/utility.py +++ b/tools/infer/utility.py @@ -542,7 +542,7 @@ def text_visual(texts, def base64_to_cv2(b64str): import base64 data = base64.b64decode(b64str.encode('utf8')) - data = np.fromstring(data, np.uint8) + data = np.frombuffer(data, np.uint8) data = cv2.imdecode(data, cv2.IMREAD_COLOR) return data From 4ab1c9ffcd7e5e79bf1c7c14064914847f530f2a Mon Sep 17 00:00:00 2001 From: Evezerest <50011306+Evezerest@users.noreply.github.com> Date: Mon, 4 Jul 2022 21:15:19 +0800 Subject: [PATCH 06/14] Merge pull request #6585 from maxbachmann/release/2.5 replace GPL licensed components --- ppocr/metrics/rec_metric.py | 5 +-- .../table/table_metric/table_metric.py | 41 ++----------------- .../vqa/tools/eval_with_label_end2end.py | 2 +- requirements.txt | 2 +- 4 files changed, 8 insertions(+), 42 deletions(-) diff --git a/ppocr/metrics/rec_metric.py b/ppocr/metrics/rec_metric.py index d858ae28e9..9863978116 100644 --- a/ppocr/metrics/rec_metric.py +++ b/ppocr/metrics/rec_metric.py @@ -12,7 +12,7 @@ # See the License for the specific language governing permissions and # limitations under the License. -import Levenshtein +from rapidfuzz.distance import Levenshtein import string @@ -46,8 +46,7 @@ class RecMetric(object): if self.is_filter: pred = self._normalize_text(pred) target = self._normalize_text(target) - norm_edit_dis += Levenshtein.distance(pred, target) / max( - len(pred), len(target), 1) + norm_edit_dis += Levenshtein.normalized_distance(pred, target) if pred == target: correct_num += 1 all_num += 1 diff --git a/ppstructure/table/table_metric/table_metric.py b/ppstructure/table/table_metric/table_metric.py index 9aca98ad78..923a9c0071 100755 --- a/ppstructure/table/table_metric/table_metric.py +++ b/ppstructure/table/table_metric/table_metric.py @@ -9,7 +9,7 @@ # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # Apache 2.0 License for more details. -import distance +from rapidfuzz.distance import Levenshtein from apted import APTED, Config from apted.helpers import Tree from lxml import etree, html @@ -39,17 +39,6 @@ class TableTree(Tree): class CustomConfig(Config): - @staticmethod - def maximum(*sequences): - """Get maximum possible value - """ - return max(map(len, sequences)) - - def normalized_distance(self, *sequences): - """Get distance from 0 to 1 - """ - return float(distance.levenshtein(*sequences)) / self.maximum(*sequences) - def rename(self, node1, node2): """Compares attributes of trees""" #print(node1.tag) @@ -58,23 +47,12 @@ class CustomConfig(Config): if node1.tag == 'td': if node1.content or node2.content: #print(node1.content, ) - return self.normalized_distance(node1.content, node2.content) + return Levenshtein.normalized_distance(node1.content, node2.content) return 0. class CustomConfig_del_short(Config): - @staticmethod - def maximum(*sequences): - """Get maximum possible value - """ - return max(map(len, sequences)) - - def normalized_distance(self, *sequences): - """Get distance from 0 to 1 - """ - return float(distance.levenshtein(*sequences)) / self.maximum(*sequences) - def rename(self, node1, node2): """Compares attributes of trees""" if (node1.tag != node2.tag) or (node1.colspan != node2.colspan) or (node1.rowspan != node2.rowspan): @@ -90,21 +68,10 @@ class CustomConfig_del_short(Config): node1_content = ['####'] if len(node2_content) < 3: node2_content = ['####'] - return self.normalized_distance(node1_content, node2_content) + return Levenshtein.normalized_distance(node1_content, node2_content) return 0. class CustomConfig_del_block(Config): - @staticmethod - def maximum(*sequences): - """Get maximum possible value - """ - return max(map(len, sequences)) - - def normalized_distance(self, *sequences): - """Get distance from 0 to 1 - """ - return float(distance.levenshtein(*sequences)) / self.maximum(*sequences) - def rename(self, node1, node2): """Compares attributes of trees""" if (node1.tag != node2.tag) or (node1.colspan != node2.colspan) or (node1.rowspan != node2.rowspan): @@ -120,7 +87,7 @@ class CustomConfig_del_block(Config): while ' ' in node2_content: print(node2_content.index(' ')) node2_content.pop(node2_content.index(' ')) - return self.normalized_distance(node1_content, node2_content) + return Levenshtein.normalized_distance(node1_content, node2_content) return 0. class TEDS(object): diff --git a/ppstructure/vqa/tools/eval_with_label_end2end.py b/ppstructure/vqa/tools/eval_with_label_end2end.py index b13ffb568f..b0fd84363f 100644 --- a/ppstructure/vqa/tools/eval_with_label_end2end.py +++ b/ppstructure/vqa/tools/eval_with_label_end2end.py @@ -20,7 +20,7 @@ from shapely.geometry import Polygon import numpy as np from collections import defaultdict import operator -import Levenshtein +from rapidfuzz.distance import Levenshtein import argparse import json import copy diff --git a/requirements.txt b/requirements.txt index b15176db3e..976d29192a 100644 --- a/requirements.txt +++ b/requirements.txt @@ -6,7 +6,7 @@ lmdb tqdm numpy visualdl -python-Levenshtein +rapidfuzz opencv-contrib-python==4.4.0.46 cython lxml From d151c6201cbc6408918ab1a6bec9df546db88773 Mon Sep 17 00:00:00 2001 From: Evezerest <50011306+Evezerest@users.noreply.github.com> Date: Thu, 23 Jun 2022 21:23:58 +0800 Subject: [PATCH 07/14] Merge pull request #6575 from Eling486/release/2.5 update win doc --- deploy/cpp_infer/docs/windows_vs2019_build.md | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/deploy/cpp_infer/docs/windows_vs2019_build.md b/deploy/cpp_infer/docs/windows_vs2019_build.md index 4f391d9250..bcaefa46f8 100644 --- a/deploy/cpp_infer/docs/windows_vs2019_build.md +++ b/deploy/cpp_infer/docs/windows_vs2019_build.md @@ -109,8 +109,10 @@ CUDA_LIB、CUDNN_LIB、TENSORRT_DIR、WITH_GPU、WITH_TENSORRT 运行之前，将下面文件拷贝到`build/Release/`文件夹下 1. `paddle_inference/paddle/lib/paddle_inference.dll` -2. `opencv/build/x64/vc15/bin/opencv_world455.dll` -3. 如果使用openblas版本的预测库还需要拷贝 `paddle_inference/third_party/install/openblas/lib/openblas.dll` +2. `paddle_inference/third_party/install/onnxruntime/lib/onnxruntime.dll` +3. `paddle_inference/third_party/install/paddle2onnx/lib/paddle2onnx.dll` +4. `opencv/build/x64/vc15/bin/opencv_world455.dll` +5. 如果使用openblas版本的预测库还需要拷贝 `paddle_inference/third_party/install/openblas/lib/openblas.dll` ### Step4: 预测 From 9a417d19aaabaae32e7c28eb296848571c62d58e Mon Sep 17 00:00:00 2001 From: Double_V Date: Mon, 13 Jun 2022 10:11:29 +0800 Subject: [PATCH 08/14] Merge pull request #6477 from MikoyChinese/fix-copy-paste Fix copy_paste no texts augment. --- ppocr/data/imaug/copy_paste.py | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/ppocr/data/imaug/copy_paste.py b/ppocr/data/imaug/copy_paste.py index 0b3386c896..79343da60f 100644 --- a/ppocr/data/imaug/copy_paste.py +++ b/ppocr/data/imaug/copy_paste.py @@ -35,10 +35,12 @@ class CopyPaste(object): point_num = data['polys'].shape[1] src_img = data['image'] src_polys = data['polys'].tolist() + src_texts = data['texts'] src_ignores = data['ignore_tags'].tolist() ext_data = data['ext_data'][0] ext_image = ext_data['image'] ext_polys = ext_data['polys'] + ext_texts = ext_data['texts'] ext_ignores = ext_data['ignore_tags'] indexs = [i for i in range(len(ext_ignores)) if not ext_ignores[i]] @@ -53,7 +55,7 @@ class CopyPaste(object): src_img = cv2.cvtColor(src_img, cv2.COLOR_BGR2RGB) ext_image = cv2.cvtColor(ext_image, cv2.COLOR_BGR2RGB) src_img = Image.fromarray(src_img).convert('RGBA') - for poly, tag in zip(select_polys, select_ignores): + for idx, poly, tag in zip(select_idxs, select_polys, select_ignores): box_img = get_rotate_crop_image(ext_image, poly) src_img, box = self.paste_img(src_img, box_img, src_polys) @@ -62,6 +64,7 @@ class CopyPaste(object): for _ in range(len(box), point_num): box.append(box[-1]) src_polys.append(box) + src_texts.append(ext_texts[idx]) src_ignores.append(tag) src_img = cv2.cvtColor(np.array(src_img), cv2.COLOR_RGB2BGR) h, w = src_img.shape[:2] @@ -70,6 +73,7 @@ class CopyPaste(object): src_polys[:, :, 1] = np.clip(src_polys[:, :, 1], 0, h) data['image'] = src_img data['polys'] = src_polys + data['texts'] = src_texts data['ignore_tags'] = np.array(src_ignores) return data From 1d5bdf6fbc96290982f9f6a00f2b779c25d06b42 Mon Sep 17 00:00:00 2001 From: Evezerest <50011306+Evezerest@users.noreply.github.com> Date: Thu, 16 Jun 2022 13:11:23 +0800 Subject: [PATCH 09/14] Merge pull request #6361 from mohamadmansourX/patch-9 Update README_en.md --- deploy/slim/quantization/README_en.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/deploy/slim/quantization/README_en.md b/deploy/slim/quantization/README_en.md index 33b2c4784a..c6796ae9dc 100644 --- a/deploy/slim/quantization/README_en.md +++ b/deploy/slim/quantization/README_en.md @@ -73,4 +73,4 @@ python deploy/slim/quantization/export_model.py -c configs/det/ch_ppocr_v2.0/ch_ The numerical range of the quantized model parameters derived from the above steps is still FP32, but the numerical range of the parameters is int8. The derived model can be converted through the `opt tool` of PaddleLite. -For quantitative model deployment, please refer to [Mobile terminal model deployment](../../lite/readme_en.md) +For quantitative model deployment, please refer to [Mobile terminal model deployment](../../lite/readme.md) From 373d1c9400273f95ea56ce7b88059a28de83de0f Mon Sep 17 00:00:00 2001 From: Leif <4603009@qq.com> Date: Wed, 24 Aug 2022 08:44:43 +0800 Subject: [PATCH 10/14] add icons --- PDF2WORD.md | 42 ++ ScreenShotWidget.py | 1108 +++++++++++++++++++++++++++++++++++++++++ icons/chinese.png | Bin 0 -> 2670 bytes icons/english.png | Bin 0 -> 2888 bytes icons/folder-open.png | Bin 0 -> 2491 bytes icons/folder-plus.png | Bin 0 -> 2598 bytes image2doc.py | 349 +++++++++++++ 7 files changed, 1499 insertions(+) create mode 100644 PDF2WORD.md create mode 100644 ScreenShotWidget.py create mode 100644 icons/chinese.png create mode 100644 icons/english.png create mode 100644 icons/folder-open.png create mode 100644 icons/folder-plus.png create mode 100644 image2doc.py diff --git a/PDF2WORD.md b/PDF2WORD.md new file mode 100644 index 0000000000..382a0febee --- /dev/null +++ b/PDF2WORD.md @@ -0,0 +1,42 @@ +# PDF2WORD + +PDF2WORD是PaddleOCR社区开发者@whj 基于PP-Structure智能文档分析系统实现的PDF转换word应用程序，提供可直接安装的exe，方便windows用户运行 + +
+ +
+ +## 1.使用 + +### 应用程序 + +1. 下载与安装：针对Windows用户，根据[软件下载]()一节下载软件后，运行 `pdf2word.exe` 。若您下载的是lite版本，安装过程中会在线下载环境依赖、模型等必要资源，安装时间较长，请确保网络畅通。serve版本打包了相关依赖，安装时间较短，可按需下载。 + +2. 转换：由于PP-Structure根据中英文数据分别进行适配，在转换相应文件时可**根据文档语言进行相应选择**。 + +### 脚本运行 + +首次运行需要将 + +``` +python pdf2word.py +``` + + + +## 2.自行打包 + +PDF2WORD应用程序通过[QPT](https://github.com/QPT-Family/QPT)工具打包实现，若您修改了界面代码需要重新打包，请在 `ppstructure` 文件夹下运行下方指令 + +``` +cd ./ +mv ./ppstructure/pdf2word .. -r +python GenEXE.py +``` + + + +## 3.软件下载 + +如需获取已打包程序，可以扫描下方二维码，关注公众号填写问卷后，加入PaddleOCR官方交流群免费获取20G OCR学习大礼包，内含OCR场景应用集合（包含数码管、液晶屏、车牌、高精度SVTR模型等7个垂类模型）、《动手学OCR》电子书、课程回放视频、前沿论文等重磅资料 + diff --git a/ScreenShotWidget.py b/ScreenShotWidget.py new file mode 100644 index 0000000000..87d46198c0 --- /dev/null +++ b/ScreenShotWidget.py @@ -0,0 +1,1108 @@ +# coding=utf-8 +# author: fardeas +# from: https://blog.csdn.net/u010501845/article/details/124931326 +import os +import sys +from datetime import datetime + +from qtpy import QtCore, QtGui +from qtpy.QtWidgets import * +from qtpy.QtCore import * +from qtpy.QtGui import * + + +class TextInputWidget(QTextEdit): + '''在截图区域内的文本输入框''' + + def __init__(self, god=None): + super().__init__(god) + self.god = god + # 设置背景透明 + # self.setStyleSheet("QTextEdit{background-color: transparent;}") + palette = self.palette() + palette.setBrush(QtGui.QPalette.ColorRole.Base, self.god.color_transparent) + self.setPalette(palette) + self.setTextColor(self.god.toolbar.curColor()) + self.setCurrentFont(self.god.toolbar.curFont()) + self._doc = self.document() # QTextDocument + self.textChanged.connect(self.adjustSizeByContent) + self.adjustSizeByContent() # 初始化调整高度为一行 + self.hide() + + def adjustSizeByContent(self, margin=30): + '''限制宽度不超出截图区域，根据文本内容调整高度，不会出现滚动条''' + self._doc.setTextWidth(self.viewport().width()) + margins = self.contentsMargins() + h = int(self._doc.size().height() + margins.top() + margins.bottom()) + self.setFixedHeight(h) + + def beginNewInput(self, pos, endPointF): + '''开始新的文本输入''' + self._maxRect = self.god.screenArea.normalizeRectF(pos, endPointF) + self.waitForInput() + + def waitForInput(self): + self.setGeometry(self._maxRect.toRect()) + # self.setGeometry(self._maxRect.adjusted(0, 0, -1, 0)) # 宽度-1 + self.setFocus() + self.show() + + def loadTextInputBy(self, action): + '''载入修改旧的文本 + action:(type, color, font, rectf, txt)''' + self.setTextColor(action[1]) + self.setCurrentFont(action[2]) + self._maxRect = action[3] + self.append(action[4]) + self.god.isDrawing = True + self.waitForInput() + + +class LineWidthAction(QAction): + + '''画笔粗细选择器''' + + def __init__(self, text, parent, lineWidth): + super().__init__(text, parent) + self._lineWidth = lineWidth + self.refresh(QtCore.Qt.GlobalColor.red) + self.triggered.connect(self.onTriggered) + self.setVisible(False) + + def refresh(self, color): + painter = self.parent().god.screenArea._painter + dotRadius = QPointF(self._lineWidth, self._lineWidth) + centerPoint = self.parent().iconPixmapCenter() + pixmap = self.parent().iconPixmapCopy() + painter.begin(pixmap) + painter.setPen(self.parent().god.pen_transparent) + painter.setBrush(color) + painter.drawEllipse(QRectF(centerPoint - dotRadius, centerPoint + dotRadius)) + painter.end() + self.setIcon(QIcon(pixmap)) + + def onTriggered(self): + self.parent()._curLineWidth = self._lineWidth + + +class FontAction(QAction): + + '''字体选择器''' + + def __init__(self, text, parent): + super().__init__(text, parent) + self.setIcon(QIcon(r"img/sys/font.png")) + self._curFont = self.parent().god.font_textInput + self.triggered.connect(self.onTriggered) + self.setVisible(False) + + def onTriggered(self): + font, ok = QFontDialog.getFont(self._curFont, self.parent(), caption='选择字体') + if ok: + self._curFont = font + self.parent().god.textInputWg.setCurrentFont(font) + + +class ColorAction(QAction): + + '''颜色选择器''' + + def __init__(self, text, parent): + super().__init__(text, parent) + self._curColor = QtCore.Qt.GlobalColor.red + self._pixmap = QPixmap(32, 32) + self.refresh(self._curColor) + self.triggered.connect(self.onTriggered) + + def refresh(self, color): + self._curColor = color + self._pixmap.fill(color) + self.setIcon(QIcon(self._pixmap)) + self.parent()._at_line_small.refresh(color) + self.parent()._at_line_normal.refresh(color) + self.parent()._at_line_big.refresh(color) + + def onTriggered(self): + col = QColorDialog.getColor(self._curColor, self.parent(), title='选择颜色') + if col.isValid(): + self.refresh(col) + self.parent().god.textInputWg.setTextColor(col) + + +class ScreenShotToolBar(QToolBar): + '''截图区域工具条''' + + def __init__(self, god): + super().__init__(god) + self.god = god + self.setToolButtonStyle(QtCore.Qt.ToolButtonStyle.ToolButtonTextUnderIcon) + self.setStyleSheet("QToolBar {border-radius: 5px;padding: 3px;background-color: #eeeeef;}") + self._style_normal = "QToolBar QToolButton{color: black;}" + self._style_selected = "QToolBar QToolButton{color: #ff7300;border: 1px solid #BEDAF2;background-color: #D6E4F1}" # 与鼠标悬停样式一样 + self._iconPixmap = QPixmap(32, 32) + self._iconPixmap.fill(self.god.color_transparent) + self._iconPixmapCenter = QPointF(self._iconPixmap.rect().center()) + self._curLineWidth = 3 + self._at_line_small = LineWidthAction('细', self, self._curLineWidth - 2) + self._at_line_normal = LineWidthAction('中', self, self._curLineWidth) + self._at_line_big = LineWidthAction('粗', self, self._curLineWidth + 2) + self._at_font = FontAction('字体', self) + self._at_color = ColorAction('颜色', self) + # self._at_rectangle = QAction(QIcon(r"img/sys/rectangle.png"), '矩形', self, triggered=self.beforeDrawRectangle) + # self._at_ellipse = QAction(QIcon(r"img/sys/ellipse.png"), '椭圆', self, triggered=self.beforeDrawEllipse) + # self._at_graffiti = QAction(QIcon(r"img/sys/graffiti.png"), '涂鸦', self, triggered=self.beforeDrawGraffiti) + # self._at_textInput = QAction(QIcon(r"img/sys/write.png"), '文字', self, triggered=self.beforeDrawText) + # self.addAction(self._at_line_small) + # self.addAction(self._at_line_normal) + # self.addAction(self._at_line_big) + # self.addAction(self._at_font) + # self.addAction(self._at_color) + # self.addSeparator() + # self.addAction(self._at_rectangle) + # self.addAction(self._at_ellipse) + # self.addAction(self._at_graffiti) + # self.addAction(self._at_textInput) + # self.addAction(QAction(QIcon(r"img/sys/undo.png"), '撤销', self, triggered=self.undo)) + # self.addSeparator() + self.addAction(QAction(QApplication.style().standardIcon(40), + '退出', self, triggered=self.god.rejectSlot)) + self.addAction(QAction(QApplication.style().standardIcon(45), + '接受', self, triggered=self.god.acceptSlot)) + # self.addAction(QAction(QIcon(r"img/chat/download.png"), '保存', self, triggered=lambda: self.beforeSave('local'))) + # self.addAction(QAction(QIcon(r"img/chat/sendImg.png"), '复制', self, triggered=lambda: self.beforeSave('clipboard'))) + # self.actionTriggered.connect(self.onActionTriggered) + + def curLineWidth(self): + return self._curLineWidth + + def curFont(self): + return self._at_font._curFont + + def curColor(self): + return self._at_color._curColor + # return QColor(self._at_color._curColor.toRgb()) # 颜色的副本 + + def iconPixmapCopy(self): + return self._iconPixmap.copy() + + def iconPixmapCenter(self): + return self._iconPixmapCenter + + # def onActionTriggered(self, action): + # '''突出显示已选中的画笔粗细、编辑模式''' + # for at in [self._at_line_small, self._at_line_normal, self._at_line_big]: + # if at._lineWidth == self._curLineWidth: + # self.widgetForAction(at).setStyleSheet(self._style_selected) + # else: + # self.widgetForAction(at).setStyleSheet(self._style_normal) + # if self.god.isDrawRectangle: + # self.widgetForAction(self._at_rectangle).setStyleSheet(self._style_selected) + # else: + # self.widgetForAction(self._at_rectangle).setStyleSheet(self._style_normal) + # if self.god.isDrawEllipse: + # self.widgetForAction(self._at_ellipse).setStyleSheet(self._style_selected) + # else: + # self.widgetForAction(self._at_ellipse).setStyleSheet(self._style_normal) + # if self.god.isDrawGraffiti: + # self.widgetForAction(self._at_graffiti).setStyleSheet(self._style_selected) + # else: + # self.widgetForAction(self._at_graffiti).setStyleSheet(self._style_normal) + # if self.god.isDrawText: + # self.widgetForAction(self._at_textInput).setStyleSheet(self._style_selected) + # else: + # self.widgetForAction(self._at_textInput).setStyleSheet(self._style_normal) + + def setLineWidthActionVisible(self, flag): + self._at_line_small.setVisible(flag) + self._at_line_normal.setVisible(flag) + self._at_line_big.setVisible(flag) + + def beforeDrawRectangle(self): + self.god.clearEditFlags() + self.god.isDrawRectangle = True + self.setLineWidthActionVisible(True) + self._at_font.setVisible(False) + + def beforeDrawEllipse(self): + self.god.clearEditFlags() + self.god.isDrawEllipse = True + self.setLineWidthActionVisible(True) + self._at_font.setVisible(False) + + def beforeDrawGraffiti(self): + self.god.clearEditFlags() + self.god.isDrawGraffiti = True + self.setLineWidthActionVisible(True) + self._at_font.setVisible(False) + + def beforeDrawText(self): + self.god.clearEditFlags() + self.god.isDrawText = True + self.setLineWidthActionVisible(False) + self._at_font.setVisible(True) + + def undo(self): + '''撤销上次编辑行为''' + if self.god.screenArea.undoEditAction(): + self.god.update() + + def beforeSave(self, target): + # 若正在编辑文本未保存，先完成编辑 + if self.god.isDrawing and self.god.isDrawText: + self.god.screenArea.saveTextInputAction() + if target == 'local': + self.god.save2Local() + elif target == 'clipboard': + self.god.save2Clipboard() + + def enterEvent(self, event): + self.god.setCursor(QtCore.Qt.CursorShape.ArrowCursor) # 工具条上显示标准箭头cursor + + def leaveEvent(self, event): + self.god.setCursor(QtCore.Qt.CursorShape.CrossCursor) # 十字无箭头 + + +class ScreenArea(QtCore.QObject): + '''屏幕区域（提供各种算法的核心类），划分为9个子区域： + TopLeft，Top，TopRight + Left，Center，Right + BottomLeft，Bottom，BottomRight + 其中Center根据start、end两个QPointF确定 + ''' + + def __init__(self, god): + super().__init__() + self.god = god + self._pt_start = QPointF() # 划定截图区域时鼠标左键按下的位置（topLeft） + self._pt_end = QPointF() # 划定截图区域时鼠标左键松开的位置（bottomRight） + self._rt_toolbar = QRectF() # 工具条的矩形 + self._actions = [] # 在截图区域上的所有编辑行为（矩形、椭圆、涂鸦、文本输入等） + self._pt_startEdit = QPointF() # 在截图区域上绘制矩形、椭圆时鼠标左键按下的位置（topLeft） + self._pt_endEdit = QPointF() # 在截图区域上绘制矩形、椭圆时鼠标左键松开的位置（bottomRight） + self._pointfs = [] # 涂鸦经过的所有点 + self._painter = QPainter() # 独立于ScreenShotWidget之外的画家类 + self._textOption = QtGui.QTextOption(QtCore.Qt.AlignmentFlag.AlignLeft | QtCore.Qt.AlignmentFlag.AlignTop) + self._textOption.setWrapMode(QtGui.QTextOption.WrapMode.WrapAnywhere) # 文本在矩形内自动换行 + # self._textOption.setWrapMode(QtGui.QTextOption.WrapMode.WrapAtWordBoundaryOrAnywhere) + self.captureScreen() + + def captureScreen(self): + '''抓取整个屏幕的截图''' + # screen = QtGui.QGuiApplication.primaryScreen() + self._screenPixmap = QApplication.primaryScreen().grabWindow(0) + self._pixelRatio = self._screenPixmap.devicePixelRatio() # 设备像素比 + self._rt_screen = self.screenLogicalRectF() + self.remakeNightArea() + + def normalizeRectF(self, topLeftPoint, bottomRightPoint): + '''根据起止点生成宽高非负数的QRectF，通常用于bottomRightPoint比topLeftPoint更左更上的情况 + 入参可以是QPoint或QPointF''' + rectf = QRectF(topLeftPoint, bottomRightPoint) + x = rectf.x() + y = rectf.y() + w = rectf.width() + h = rectf.height() + if w < 0: # bottomRightPoint在topLeftPoint左侧时，topLeftPoint往左移动 + x = x + w + w = -w + if h < 0: # bottomRightPoint在topLeftPoint上侧时，topLeftPoint往上移动 + y = y + h + h = -h + return QRectF(x, y, w, h) + + def physicalRectF(self, rectf): + '''计算划定的截图区域的（缩放倍率1.0的）原始矩形（会变大） + rectf：划定的截图区域的矩形。可为QRect或QRectF''' + return QRectF(rectf.x() * self._pixelRatio, rectf.y() * self._pixelRatio, + rectf.width() * self._pixelRatio, rectf.height() * self._pixelRatio) + + def logicalRectF(self, physicalRectF): + '''根据原始矩形计算缩放后的矩形（会变小） + physicalRectF：缩放倍率1.0的原始矩形。可为QRect或QRectF''' + return QRectF(physicalRectF.x() / self._pixelRatio, physicalRectF.y() / self._pixelRatio, + physicalRectF.width() / self._pixelRatio, physicalRectF.height() / self._pixelRatio) + + def physicalPixmap(self, rectf, editAction=False): + '''根据指定区域获取其原始大小的（缩放倍率1.0的）QPixmap + rectf：指定区域。可为QRect或QRectF + editAction:是否带上编辑结果''' + if editAction: + canvasPixmap = self.screenPhysicalPixmapCopy() + self._painter.begin(canvasPixmap) + self.paintEachEditAction(self._painter, textBorder=False) + self._painter.end() + return canvasPixmap.copy(self.physicalRectF(rectf).toRect()) + else: + return self._screenPixmap.copy(self.physicalRectF(rectf).toRect()) + + def screenPhysicalRectF(self): + return QRectF(self._screenPixmap.rect()) + + def screenLogicalRectF(self): + return QRectF(QPointF(0, 0), self.screenLogicalSizeF()) # 即当前屏幕显示的大小 + + def screenPhysicalSizeF(self): + return QSizeF(self._screenPixmap.size()) + + def screenLogicalSizeF(self): + return QSizeF(self._screenPixmap.width() / self._pixelRatio, self._screenPixmap.height() / self._pixelRatio) + + def screenPhysicalPixmapCopy(self): + return self._screenPixmap.copy() + + def screenLogicalPixmapCopy(self): + return self._screenPixmap.scaled(self.screenLogicalSizeF().toSize()) + + def centerPhysicalRectF(self): + return self.physicalRectF(self._rt_center) + + def centerLogicalRectF(self): + '''根据屏幕上的start、end两个QPointF确定''' + return self._rt_center + + def centerPhysicalPixmap(self, editAction=True): + '''截图区域的QPixmap + editAction:是否带上编辑结果''' + return self.physicalPixmap(self._rt_center + QMarginsF(-1, -1, 1, 1), editAction=editAction) + + def centerTopMid(self): + return self._pt_centerTopMid + + def centerBottomMid(self): + return self._pt_centerBottomMid + + def centerLeftMid(self): + return self._pt_centerLeftMid + + def centerRightMid(self): + return self._pt_centerRightMid + + def setStartPoint(self, pointf, remake=False): + self._pt_start = pointf + if remake: + self.remakeNightArea() + + def setEndPoint(self, pointf, remake=False): + self._pt_end = pointf + if remake: + self.remakeNightArea() + + def setCenterArea(self, start, end): + self._pt_start = start + self._pt_end = end + self.remakeNightArea() + + def remakeNightArea(self): + '''重新划分九宫格区域。根据中央截图区域计算出来的其他8个区域、截图区域四个边框中点坐标等都是logical的''' + self._rt_center = self.normalizeRectF(self._pt_start, self._pt_end) + # 中央区域上下左右边框的中点，用于调整大小 + self._pt_centerTopMid = (self._rt_center.topLeft() + self._rt_center.topRight()) / 2 + self._pt_centerBottomMid = (self._rt_center.bottomLeft() + self._rt_center.bottomRight()) / 2 + self._pt_centerLeftMid = (self._rt_center.topLeft() + self._rt_center.bottomLeft()) / 2 + self._pt_centerRightMid = (self._rt_center.topRight() + self._rt_center.bottomRight()) / 2 + # 以截图区域左上、上中、右上、左中、右中、左下、下中、右下为中心的正方形区域，用于调整大小 + self._square_topLeft = self.squareAreaByCenter(self._rt_center.topLeft()) + self._square_topRight = self.squareAreaByCenter(self._rt_center.topRight()) + self._square_bottomLeft = self.squareAreaByCenter(self._rt_center.bottomLeft()) + self._square_bottomRight = self.squareAreaByCenter(self._rt_center.bottomRight()) + self._square_topMid = self.squareAreaByCenter(self._pt_centerTopMid) + self._square_bottomMid = self.squareAreaByCenter(self._pt_centerBottomMid) + self._square_leftMid = self.squareAreaByCenter(self._pt_centerLeftMid) + self._square_rightMid = self.squareAreaByCenter(self._pt_centerRightMid) + # 除中央截图区域外的8个区域 + self._rt_topLeft = QRectF(self._rt_screen.topLeft(), self._rt_center.topLeft()) + self._rt_top = QRectF(QPointF(self._rt_center.topLeft().x(), 0), self._rt_center.topRight()) + self._rt_topRight = QRectF(QPointF(self._rt_center.topRight().x(), 0), QPointF(self._rt_screen.width(), self._rt_center.topRight().y())) + self._rt_left = QRectF(QPointF(0, self._rt_center.topLeft().y()), self._rt_center.bottomLeft()) + self._rt_right = QRectF(self._rt_center.topRight(), QPointF(self._rt_screen.width(), self._rt_center.bottomRight().y())) + self._rt_bottomLeft = QRectF(QPointF(0, self._rt_center.bottomLeft().y()), QPointF(self._rt_center.bottomLeft().x(), self._rt_screen.height())) + self._rt_bottom = QRectF(self._rt_center.bottomLeft(), QPointF(self._rt_center.bottomRight().x(), self._rt_screen.height())) + self._rt_bottomRight = QRectF(self._rt_center.bottomRight(), self._rt_screen.bottomRight()) + + def squareAreaByCenter(self, pointf): + '''以QPointF为中心的正方形QRectF''' + rectf = QRectF(0, 0, 15, 15) + rectf.moveCenter(pointf) + return rectf + + def aroundAreaIn8Direction(self): + '''中央区域周边的8个方向的区域（无交集）''' + return [self._rt_topLeft, self._rt_top, self._rt_topRight, + self._rt_left, self._rt_right, + self._rt_bottomLeft, self._rt_bottom, self._rt_bottomRight] + + def aroundAreaIn4Direction(self): + '''中央区域周边的4个方向的区域（有交集） + 上区域(左上、上、右上)：0, 0, maxX, topRight.y + 下区域(左下、下、右下)：0, bottomLeft.y, maxX, maxY-bottomLeft.y + 左区域(左上、左、左下)：0, 0, bottomLeft.x, maxY + 右区域(右上、右、右下)：topRight.x, 0, maxX - topRight.x, maxY''' + screenSizeF = self.screenLogicalSizeF() + pt_topRight = self._rt_center.topRight() + pt_bottomLeft = self._rt_center.bottomLeft() + return [QRectF(0, 0, screenSizeF.width(), pt_topRight.y()), + QRectF(0, pt_bottomLeft.y(), screenSizeF.width(), screenSizeF.height() - pt_bottomLeft.y()), + QRectF(0, 0, pt_bottomLeft.x(), screenSizeF.height()), + QRectF(pt_topRight.x(), 0, screenSizeF.width() - pt_topRight.x(), screenSizeF.height())] + + def aroundAreaWithoutIntersection(self): + '''中央区域周边的4个方向的区域（无交集） + 上区域(左上、上、右上)：0, 0, maxX, topRight.y + 下区域(左下、下、右下)：0, bottomLeft.y, maxX, maxY-bottomLeft.y + 左区域(左)：0, topRight.y, bottomLeft.x-1, center.height + 右区域(右)：topRight.x+1, topRight.y, maxX - topRight.x, center.height''' + screenSizeF = self.screenLogicalSizeF() + pt_topRight = self._rt_center.topRight() + pt_bottomLeft = self._rt_center.bottomLeft() + centerHeight = pt_bottomLeft.y() - pt_topRight.y() + return [QRectF(0, 0, screenSizeF.width(), pt_topRight.y()), + QRectF(0, pt_bottomLeft.y(), screenSizeF.width(), screenSizeF.height() - pt_bottomLeft.y()), + QRectF(0, pt_topRight.y(), pt_bottomLeft.x() - 1, centerHeight), + QRectF(pt_topRight.x() + 1, pt_topRight.y(), screenSizeF.width() - pt_topRight.x(), centerHeight)] + + def setBeginDragPoint(self, pointf): + '''计算开始拖拽位置距离截图区域左上角的向量''' + self._drag_vector = pointf - self._rt_center.topLeft() + + def getNewPosAfterDrag(self, pointf): + '''计算拖拽后截图区域左上角的新位置''' + return pointf - self._drag_vector + + def moveCenterAreaTo(self, pointf): + '''限制拖拽不能超出屏幕范围''' + self._rt_center.moveTo(self.getNewPosAfterDrag(pointf)) + startPointF = self._rt_center.topLeft() + if startPointF.x() < 0: + self._rt_center.moveTo(0, startPointF.y()) + startPointF = self._rt_center.topLeft() + if startPointF.y() < 0: + self._rt_center.moveTo(startPointF.x(), 0) + screenSizeF = self.screenLogicalSizeF() + endPointF = self._rt_center.bottomRight() + if endPointF.x() > screenSizeF.width(): + self._rt_center.moveBottomRight(QPointF(screenSizeF.width(), endPointF.y())) + endPointF = self._rt_center.bottomRight() + if endPointF.y() > screenSizeF.height(): + self._rt_center.moveBottomRight(QPointF(endPointF.x(), screenSizeF.height())) + self.setCenterArea(self._rt_center.topLeft(), self._rt_center.bottomRight()) + + def setBeginAdjustPoint(self, pointf): + '''判断开始调整截图区域大小时鼠标左键在哪个区（不可能是中央区域），用于判断调整大小的意图方向''' + self._mousePos = self.getMousePosBy(pointf) + + def getMousePosBy(self, pointf): + if self._square_topLeft.contains(pointf): + return 'TL' + elif self._square_topMid.contains(pointf): + return 'T' + elif self._square_topRight.contains(pointf): + return 'TR' + elif self._square_leftMid.contains(pointf): + return 'L' + elif self._rt_center.contains(pointf): + return 'CENTER' + elif self._square_rightMid.contains(pointf): + return 'R' + elif self._square_bottomLeft.contains(pointf): + return 'BL' + elif self._square_bottomMid.contains(pointf): + return 'B' + elif self._square_bottomRight.contains(pointf): + return 'BR' + else: + return 'ERROR' + + def adjustCenterAreaBy(self, pointf): + '''根据开始调整截图区域大小时鼠标左键在哪个区（不可能是中央区域），判断调整大小的意图方向，判定新的开始、结束位置''' + startPointF = self._rt_center.topLeft() + endPointF = self._rt_center.bottomRight() + if self._mousePos == 'TL': + startPointF = pointf + elif self._mousePos == 'T': + startPointF = QPointF(startPointF.x(), pointf.y()) + elif self._mousePos == 'TR': + startPointF = QPointF(startPointF.x(), pointf.y()) + endPointF = QPointF(pointf.x(), endPointF.y()) + elif self._mousePos == 'L': + startPointF = QPointF(pointf.x(), startPointF.y()) + elif self._mousePos == 'R': + endPointF = QPointF(pointf.x(), endPointF.y()) + elif self._mousePos == 'BL': + startPointF = QPointF(pointf.x(), startPointF.y()) + endPointF = QPointF(endPointF.x(), pointf.y()) + elif self._mousePos == 'B': + endPointF = QPointF(endPointF.x(), pointf.y()) + elif self._mousePos == 'BR': + endPointF = pointf + else: # 'ERROR' + return + newRectF = self.normalizeRectF(startPointF, endPointF) + self.setCenterArea(newRectF.topLeft(), newRectF.bottomRight()) + + def getMouseShapeBy(self, pointf): + '''根据鼠标位置返回对应的鼠标样式''' + if self._rt_center.contains(pointf): + if self.god.isDrawRectangle or self.god.isDrawEllipse: + return QtCore.Qt.CursorShape.ArrowCursor + elif self.god.isDrawGraffiti: + return QtCore.Qt.CursorShape.PointingHandCursor # 超链接上的手势 + elif self.god.isDrawText: + return QtCore.Qt.CursorShape.IBeamCursor # 工字 + else: + return QtCore.Qt.CursorShape.SizeAllCursor # 十字有箭头 + # return QtCore.Qt.CursorShape.OpenHandCursor # 打开的手，表示可拖拽 + elif self._square_topLeft.contains(pointf) or self._square_bottomRight.contains(pointf): + return QtCore.Qt.CursorShape.SizeFDiagCursor # ↖↘ + elif self._square_topMid.contains(pointf) or self._square_bottomMid.contains(pointf): + return QtCore.Qt.CursorShape.SizeVerCursor # ↑↓ + elif self._square_topRight.contains(pointf) or self._square_bottomLeft.contains(pointf): + return QtCore.Qt.CursorShape.SizeBDiagCursor # ↙↗ + elif self._square_leftMid.contains(pointf) or self._square_rightMid.contains(pointf): + return QtCore.Qt.CursorShape.SizeHorCursor # ←→ + else: + return QtCore.Qt.CursorShape.CrossCursor # 十字无箭头 + + def isMousePosInCenterRectF(self, pointf): + return self._rt_center.contains(pointf) + + def paintMagnifyingGlassPixmap(self, pos, glassSize): + '''绘制放大镜内的图像(含纵横十字线) + pos:鼠标光标位置 + glassSize:放大镜边框大小''' + pixmapRect = QRect(0, 0, 20, 20) # 以鼠标光标为中心的正方形区域，最好是偶数 + pixmapRect.moveCenter(pos) + glassPixmap = self.physicalPixmap(pixmapRect) + glassPixmap.setDevicePixelRatio(1.0) + glassPixmap = glassPixmap.scaled(glassSize, glassSize, QtCore.Qt.AspectRatioMode.KeepAspectRatio) + # 在放大后的QPixmap上画纵横十字线 + self._painter.begin(glassPixmap) + halfWidth = glassPixmap.width() / 2 + halfHeight = glassPixmap.height() / 2 + self._painter.setPen(self.god.pen_SolidLine_lightBlue) + self._painter.drawLine(QPointF(0, halfHeight), QPointF(glassPixmap.width(), halfHeight)) + self._painter.drawLine(QPointF(halfWidth, 0), QPointF(halfWidth, glassPixmap.height())) + self._painter.end() + return glassPixmap + + def paintEachEditAction(self, painter, textBorder=True): + '''绘制所有已保存的编辑行为。编辑行为超出截图区域也无所谓，保存图像时只截取截图区域内 + textBorder:是否绘制文本边框''' + for action in self.getEditActions(): + if action[0] == 'rectangle': # (type, color, lineWidth, startPoint, endPoint) + self.paintRectangle(painter, action[1], action[2], action[3], action[4]) + elif action[0] == 'ellipse': # (type, color, lineWidth, startPoint, endPoint) + self.paintEllipse(painter, action[1], action[2], action[3], action[4]) + elif action[0] == 'graffiti': # (type, color, lineWidth, points) + self.paintGraffiti(painter, action[1], action[2], action[3]) + elif action[0] == 'text': # (type, color, font, rectf, txt) + self.paintTextInput(painter, action[1], action[2], action[3], action[4], textBorder=textBorder) + + def paintRectangle(self, painter, color, lineWidth, startPoint=None, endPoint=None): + if not startPoint: + startPoint = self._pt_startEdit + if not endPoint: + endPoint = self._pt_endEdit + qrectf = self.normalizeRectF(startPoint, endPoint) + if qrectf.isValid(): + pen = QPen(color) + pen.setWidth(lineWidth) + painter.setPen(pen) + painter.setBrush(self.god.color_transparent) + painter.drawRect(qrectf) + + def paintEllipse(self, painter, color, lineWidth, startPoint=None, endPoint=None): + if not startPoint: + startPoint = self._pt_startEdit + if not endPoint: + endPoint = self._pt_endEdit + qrectf = self.normalizeRectF(startPoint, endPoint) + if qrectf.isValid(): + pen = QPen(color) + pen.setWidth(lineWidth) + painter.setPen(pen) + painter.setBrush(self.god.color_transparent) + painter.drawEllipse(qrectf) + + def paintGraffiti(self, painter, color, lineWidth, pointfs=None): + if not pointfs: + pointfs = self.getGraffitiPointFs() + pen = QPen(color) + pen.setWidth(lineWidth) + painter.setPen(pen) + total = len(pointfs) + if total == 0: + return + elif total == 1: + painter.drawPoint(pointfs[0]) + else: + previousPoint = pointfs[0] + for i in range(1, total): + nextPoint = pointfs[i] + painter.drawLine(previousPoint, nextPoint) + previousPoint = nextPoint + + def paintTextInput(self, painter, color, font, rectf, txt, textBorder=True): + painter.setPen(color) + painter.setFont(font) + painter.drawText(rectf, txt, self._textOption) + if textBorder: + painter.setPen(QtCore.Qt.PenStyle.DotLine) # 点线 + painter.setBrush(self.god.color_transparent) + painter.drawRect(rectf) + + def getEditActions(self): + return self._actions.copy() + + def takeTextInputActionAt(self, pointf): + '''根据鼠标位置查找已保存的文本输入结果，找到后取出''' + for i in range(len(self._actions)): + action = self._actions[i] + if action[0] == 'text' and action[3].contains(pointf): + return self._actions.pop(i) + return None + + def undoEditAction(self): + reply = False + if self._actions: + reply = self._actions.pop() + if not self._actions: # 所有编辑行为都被撤销后退出编辑模式 + self.god.exitEditMode() + else: + self.god.exitEditMode() + return reply + + def clearEditActions(self): + self._actions.clear() + + def setBeginEditPoint(self, pointf): + '''在截图区域上绘制矩形、椭圆时鼠标左键按下的位置（topLeft）''' + self._pt_startEdit = pointf + self.god.isDrawing = True + + def setEndEditPoint(self, pointf): + '''在截图区域上绘制矩形、椭圆时鼠标左键松开的位置（bottomRight）''' + self._pt_endEdit = pointf + + def saveRectangleAction(self): + rectf = self.normalizeRectF(self._pt_startEdit, self._pt_endEdit) + self._actions.append(('rectangle', self.god.toolbar.curColor(), self.god.toolbar.curLineWidth(), + rectf.topLeft(), rectf.bottomRight())) + self._pt_startEdit = QPointF() + self._pt_endEdit = QPointF() + self.god.isDrawing = False + + def saveEllipseleAction(self): + rectf = self.normalizeRectF(self._pt_startEdit, self._pt_endEdit) + self._actions.append(('ellipse', self.god.toolbar.curColor(), self.god.toolbar.curLineWidth(), + rectf.topLeft(), rectf.bottomRight())) + self._pt_startEdit = QPointF() + self._pt_endEdit = QPointF() + self.god.isDrawing = False + + def saveGraffitiPointF(self, pointf, first=False): + self._pointfs.append(pointf) + if first: + self.god.isDrawing = True + + def getGraffitiPointFs(self): + return self._pointfs.copy() + + def saveGraffitiAction(self): + if self._pointfs: + self._actions.append(('graffiti', self.god.toolbar.curColor(), self.god.toolbar.curLineWidth(), self._pointfs.copy())) + self._pointfs.clear() + self.god.isDrawing = False + + def setBeginInputTextPoint(self, pointf): + '''在截图区域上输入文字时鼠标左键按下的位置（topLeft）''' + self.god.isDrawing = True + self.god.textInputWg.beginNewInput(pointf, self._pt_end) + + def saveTextInputAction(self): + txt = self.god.textInputWg.toPlainText() + if txt: + rectf = self.god.textInputWg._maxRect # 取最大矩形的topLeft + rectf.setSize(QRectF(self.god.textInputWg.rect()).size()) # 取实际矩形的宽高 + self._actions.append(('text', self.god.toolbar.curColor(), self.god.toolbar.curFont(), + rectf, txt)) + self.god.textInputWg.clear() + self.god.textInputWg.hide() # 不管保存成功与否都取消编辑 + self.god.isDrawing = False + + def saveNightAreaImg(self): + '''将九宫格区域保存为本地图片，仅用于开发测试''' + screenPixmap = self.screenPhysicalPixmapCopy() + self._painter.begin(screenPixmap) + self._painter.setPen(self.pen_SolidLine_lightBlue) + self._painter.setFont(self.god.font_normal) + self._painter.drawRect(self._rt_center) + for area in self.aroundAreaIn8Direction(): + self._painter.drawRect(area) + for pointf in [self._rt_center.topLeft(), self._rt_center.topRight(), + self._rt_center.bottomLeft(), self._rt_center.bottomRight(), + self._pt_centerTopMid, self._pt_centerBottomMid, + self._pt_centerLeftMid, self._pt_centerRightMid]: + self._painter.drawText(pointf + QPointF(5, -5), '(%s, %s)' % (pointf.x(), pointf.y())) + self._painter.end() + screenPixmap.save('1.jpg', quality=100) + self.centerPhysicalPixmap().save('2.jpg', quality=100) + + +class ScreenShotWidget(QWidget): + + fileType_all = '所有文件 (*);;Excel文件 (*.xls *.xlsx);;图片文件 (*.jpg *.jpeg *.gif *.png *.bmp)' + fileType_img = '图片文件 (*.jpg *.jpeg *.gif *.png *.bmp)' + dir_lastAccess = os.getcwd() # 最后访问目录 + + def __init__(self): + super().__init__() + self.setMouseTracking(True) + self.setWindowFlags(QtCore.Qt.WindowType.FramelessWindowHint | QtCore.Qt.WindowType.WindowStaysOnTopHint) + self.initPainterTool() + self.initFunctionalFlag() + self.screenArea = ScreenArea(self) + self.toolbar = ScreenShotToolBar(self) + self.textInputWg = TextInputWidget(self) + + self.captureImage = None + # 设置 screenPixmap 为窗口背景 + # palette = QtGui.QPalette() + # palette.setBrush(QtGui.QPalette.ColorRole.Window, QtGui.QBrush(self.screenArea.screenPhysicalPixmapCopy())) + # self.setPalette(palette) + + def rejectSlot(self): + self.captureImage = None + self.close() + + def acceptSlot(self): + self.captureImage = self.screenArea.centerPhysicalPixmap().toImage() + self.close() + + def start(self): + self.screenArea.captureScreen() + self.setGeometry(self.screenArea.screenPhysicalRectF().toRect()) + self.clearScreenShotArea() + self.showFullScreen() + + def initPainterTool(self): + self.painter = QPainter() + self.color_transparent = QtCore.Qt.GlobalColor.transparent + self.color_black = QColor(0, 0, 0, 64) # 黑色背景 + self.color_lightBlue = QColor(30, 120, 255) # 浅蓝色。深蓝色QtCore.Qt.GlobalColor.blue + self.font_normal = QtGui.QFont('Times New Roman', 11, QtGui.QFont.Weight.Normal) + self.font_textInput = QtGui.QFont('微软雅黑', 16, QtGui.QFont.Weight.Normal) # 工具条文字工具默认字体 + self.pen_transparent = QPen(QtCore.Qt.PenStyle.NoPen) # 没有笔迹，画不出线条 + self.pen_white = QPen(QtCore.Qt.GlobalColor.white) + self.pen_SolidLine_lightBlue = QPen(self.color_lightBlue) # 实线，浅蓝色 + self.pen_SolidLine_lightBlue.setStyle(QtCore.Qt.PenStyle.DashLine) # 实线SolidLine，虚线DashLine，点线DotLine + self.pen_SolidLine_lightBlue.setWidthF(0) # 0表示线宽为1 + self.pen_DashLine_lightBlue = QPen(self.color_lightBlue) # 虚线，浅蓝色 + self.pen_DashLine_lightBlue.setStyle(QtCore.Qt.PenStyle.DashLine) + + def initFunctionalFlag(self): + self.hasScreenShot = False # 是否已通过拖动鼠标左键划定截图区域 + self.isCapturing = False # 正在拖动鼠标左键选定截图区域时 + self.isMoving = False # 在截图区域内拖动时 + self.isAdjusting = False # 在截图区域的边框按住鼠标左键调整大小时 + self.isDrawing = False # 是否已在截图区域内开始绘制 + self.isDrawRectangle = False # 正在截图区域内画矩形 + self.isDrawEllipse = False # 正在截图区域内画椭圆 + self.isDrawGraffiti = False # 正在截图区域内进行涂鸦 + self.isDrawText = False # 正在截图区域内画文字 + self.setCursor(QtCore.Qt.CursorShape.CrossCursor) # 设置鼠标样式 十字 + + def paintEvent(self, event): + centerRectF = self.screenArea.centerLogicalRectF() + screenSizeF = self.screenArea.screenLogicalSizeF() + canvasPixmap = self.screenArea.screenPhysicalPixmapCopy() + # canvasPixmap = QPixmap(screenSizeF.toSize()) + # canvasPixmap.fill(self.color_transparent) + # 在屏幕截图的副本上绘制已选定的截图区域 + self.painter.begin(canvasPixmap) + if self.hasScreenShot: + self.paintCenterArea(centerRectF) # 绘制中央截图区域 + self.paintMaskLayer(screenSizeF, fullScreen=False) # 绘制截图区域的周边区域遮罩层 + else: + self.paintMaskLayer(screenSizeF) + self.paintMagnifyingGlass(screenSizeF) # 在鼠标光标右下角显示放大镜 + self.paintToolbar(centerRectF, screenSizeF) # 在截图区域右下角显示工具条 + self.paintEditActions() # 在截图区域绘制编辑行为结果 + self.painter.end() + # 把画好的绘制结果显示到窗口上 + self.painter.begin(self) + self.painter.drawPixmap(0, 0, canvasPixmap) # 从坐标(0, 0)开始绘制 + self.painter.end() + + def paintCenterArea(self, centerRectF): + '''绘制已选定的截图区域''' + self.painter.setRenderHint(QPainter.RenderHint.Antialiasing, True) # 反走样 + # 1.绘制矩形线框 + self.painter.setPen(self.pen_DashLine_lightBlue) + self.painter.drawRect(centerRectF) + # 2.绘制矩形线框4个端点和4条边框的中间点 + if centerRectF.width() >= 100 and centerRectF.height() >= 100: + points = [ # 点坐标 + centerRectF.topLeft(), centerRectF.topRight(), centerRectF.bottomLeft(), centerRectF.bottomRight(), + self.screenArea.centerLeftMid(), self.screenArea.centerRightMid(), + self.screenArea.centerTopMid(), self.screenArea.centerBottomMid() + ] + blueDotRadius = QPointF(2, 2) # 椭圆蓝点 + self.painter.setBrush(self.color_lightBlue) + for point in points: + self.painter.drawEllipse(QRectF(point - blueDotRadius, point + blueDotRadius)) + # 3.在截图区域左上角显示截图区域宽高 + if centerRectF.topLeft().y() > 20: + labelPos = centerRectF.topLeft() + QPointF(5, -5) + else: # 拖拽截图区域到贴近屏幕上边缘时“宽x高”移动到截图区域左上角的下侧 + labelPos = centerRectF.topLeft() + QPointF(5, 15) + centerPhysicalRect = self.screenArea.centerPhysicalRectF().toRect() + self.painter.setPen(self.pen_white) + self.painter.setFont(self.font_normal) + self.painter.drawText(labelPos, '%s x %s' % (centerPhysicalRect.width(), centerPhysicalRect.height())) + # 4.在屏幕左上角预览截图结果 + # self.painter.drawPixmap(0, 0, self.screenArea.centerPhysicalPixmap()) # 从坐标(0, 0)开始绘制 + + def paintMaskLayer(self, screenSizeF, fullScreen=True): + if fullScreen: # 全屏遮罩层 + maskPixmap = QPixmap(screenSizeF.toSize()) + maskPixmap.fill(self.color_black) + self.painter.drawPixmap(0, 0, maskPixmap) + else: # 绘制截图区域的周边区域遮罩层，以凸显截图区域 + # 方法一：截图区域以外的8个方向区域 + # for area in self.screenArea.aroundAreaIn8Direction(): + # area = area.normalized() + # maskPixmap = QPixmap(area.size().toSize()) # 由于float转int的精度问题，可能会存在黑线条缝隙 + # maskPixmap.fill(self.color_black) + # self.painter.drawPixmap(area.topLeft(), maskPixmap) + # 方法二：截图区域以外的上下左右区域（有交集，交集部分颜色加深，有明显的纵横效果） + # for area in self.screenArea.aroundAreaIn4Direction(): + # maskPixmap = QPixmap(area.size().toSize()) + # maskPixmap.fill(self.color_black) + # self.painter.drawPixmap(area.topLeft(), maskPixmap) + # 方法三：截图区域以外的上下左右区域（无交集） + for area in self.screenArea.aroundAreaWithoutIntersection(): + maskPixmap = QPixmap(area.size().toSize()) + maskPixmap.fill(self.color_black) + self.painter.drawPixmap(area.topLeft(), maskPixmap) + + def paintMagnifyingGlass(self, screenSizeF, glassSize=150, offset=30, labelHeight=30): + '''未划定截图区域模式时、正在划定截取区域时、调整截取区域大小时在鼠标光标右下角显示放大镜 + glassSize:放大镜正方形边长 + offset:放大镜任意一个端点距离鼠标光标位置的最近距离 + labelHeight:pos和rgb两行文字的高度''' + if self.hasScreenShot and (not self.isCapturing) and (not self.isAdjusting): + return + pos = QtGui.QCursor.pos() + glassPixmap = self.screenArea.paintMagnifyingGlassPixmap(pos, glassSize) # 画好纵横十字线后的放大镜内QPixmap + # 限制放大镜显示不超出屏幕外 + glassRect = glassPixmap.rect() + if (pos.x() + glassSize + offset) < screenSizeF.width(): + if (pos.y() + offset + glassSize + labelHeight) < screenSizeF.height(): + glassRect.moveTo(pos + QPoint(offset, offset)) + else: + glassRect.moveBottomLeft(pos + QPoint(offset, -offset)) + else: + if (pos.y() + offset + glassSize + labelHeight) < screenSizeF.height(): + glassRect.moveTopRight(pos + QPoint(-offset, offset)) + else: + glassRect.moveBottomRight(pos + QPoint(-offset, -offset)) + self.painter.drawPixmap(glassRect.topLeft(), glassPixmap) + # 显示pos:(x, y)、rgb:(255,255,255) + qrgb = QtGui.QRgba64.fromArgb32(glassPixmap.toImage().pixel(glassPixmap.rect().center())) + labelRectF = QRectF(glassRect.bottomLeft().x(), glassRect.bottomLeft().y(), glassSize, labelHeight) + self.painter.setPen(self.pen_transparent) + self.painter.setBrush(self.color_black) # 黑底 + self.painter.drawRect(labelRectF) + self.painter.setPen(self.pen_white) + self.painter.setFont(self.font_normal) + self.painter.drawText(labelRectF, + QtCore.Qt.AlignmentFlag.AlignLeft | QtCore.Qt.AlignmentFlag.AlignVCenter, + 'pos:(%s, %s)\nrgb:(%s, %s, %s)' % (pos.x(), pos.y(), qrgb.red8(), qrgb.green8(), qrgb.blue8())) + + def paintToolbar(self, centerRectF, screenSizeF): + '''在截图区域右下角显示工具条''' + if self.hasScreenShot: + if self.isCapturing or self.isAdjusting: + self.toolbar.hide() # 正在划定截取区域时、调整截图区域大小时不显示工具条 + else: + self.toolbar.adjustSize() + toolbarRectF = QRectF(self.toolbar.rect()) + # 工具条位置优先顺序：右下角下侧，右上角上侧，右下角上侧 + if (screenSizeF.height() - centerRectF.bottomRight().y()) > toolbarRectF.height(): + toolbarRectF.moveTopRight(centerRectF.bottomRight() + QPointF(-5, 5)) + elif centerRectF.topRight().y() > toolbarRectF.height(): + toolbarRectF.moveBottomRight(centerRectF.topRight() + QPointF(-5, -5)) + else: + toolbarRectF.moveBottomRight(centerRectF.bottomRight() + QPointF(-5, -5)) + # 限制工具条的x坐标不为负数，不能移出屏幕外 + if toolbarRectF.x() < 0: + pos = toolbarRectF.topLeft() + pos.setX(centerRectF.x() + 5) + toolbarRectF.moveTo(pos) + self.toolbar.move(toolbarRectF.topLeft().toPoint()) + self.toolbar.show() + else: + self.toolbar.hide() + + def paintEditActions(self): + '''在截图区域绘制编辑行为结果。编辑行为超出截图区域也无所谓，保存图像时只截取截图区域内''' + # 1.绘制正在拖拽编辑中的矩形、椭圆、涂鸦 + if self.isDrawRectangle: + self.screenArea.paintRectangle(self.painter, self.toolbar.curColor(), self.toolbar.curLineWidth()) + elif self.isDrawEllipse: + self.screenArea.paintEllipse(self.painter, self.toolbar.curColor(), self.toolbar.curLineWidth()) + elif self.isDrawGraffiti: + self.screenArea.paintGraffiti(self.painter, self.toolbar.curColor(), self.toolbar.curLineWidth()) + # 2.绘制所有已保存的编辑行为 + self.screenArea.paintEachEditAction(self.painter) + + def clearEditFlags(self): + self.isDrawing = False + self.isDrawRectangle = False + self.isDrawEllipse = False + self.isDrawGraffiti = False + self.isDrawText = False + + def exitEditMode(self): + '''退出编辑模式''' + self.clearEditFlags() + # self.toolbar.onActionTriggered(None) # 清空工具条工具按钮选中状态 + self.textInputWg.hide() + + def clearScreenShotArea(self): + '''清空已划定的截取区域''' + self.screenArea.clearEditActions() # 清除已保存的编辑行为 + self.exitEditMode() + self.hasScreenShot = False + self.isCapturing = False + pos = QPointF() + self.screenArea.setCenterArea(pos, pos) + self.update() + self.setCursor(QtCore.Qt.CursorShape.CrossCursor) # 设置鼠标样式 十字 + + def mousePressEvent(self, event): + if event.button() == QtCore.Qt.MouseButton.LeftButton: + pos = event.pos() + if self.hasScreenShot: + if self.isDrawRectangle or self.isDrawEllipse: + self.screenArea.setBeginEditPoint(pos) + elif self.isDrawGraffiti: # 保存涂鸦经过的每一个点 + self.screenArea.saveGraffitiPointF(pos, first=True) + elif self.isDrawText: + if self.isDrawing: + if QRectF(self.textInputWg.rect()).contains(pos): + pass # 在输入框内调整光标位置，忽略 + else: # 鼠标点到输入框之外，完成编辑 + self.screenArea.saveTextInputAction() + else: # 未开始编辑时（暂不支持文本拖拽） + action = self.screenArea.takeTextInputActionAt(pos) + if action: # 鼠标点到输入框之内，修改旧的文本输入 + self.textInputWg.loadTextInputBy(action) + else: # 鼠标点到输入框之外，开始新的文本输入 + self.screenArea.setBeginInputTextPoint(pos) + elif self.screenArea.isMousePosInCenterRectF(pos): + self.isMoving = True # 进入拖拽移动模式 + self.screenArea.setBeginDragPoint(pos) + else: + self.isAdjusting = True # 进入调整大小模式 + self.screenArea.setBeginAdjustPoint(pos) + else: + self.screenArea.setCenterArea(pos, pos) + self.isCapturing = True # 进入划定截图区域模式 + if event.button() == QtCore.Qt.MouseButton.RightButton: + if self.hasScreenShot or self.isCapturing: # 清空已划定的的截图区域 + self.clearScreenShotArea() + else: + self.close() + + def mouseReleaseEvent(self, event): + if event.button() == QtCore.Qt.MouseButton.LeftButton: + if self.isDrawRectangle: + self.screenArea.saveRectangleAction() + elif self.isDrawEllipse: + self.screenArea.saveEllipseleAction() + elif self.isDrawGraffiti: + self.screenArea.saveGraffitiAction() + self.isCapturing = False + self.isMoving = False + self.isAdjusting = False + self.toolbar.show() + + def mouseMoveEvent(self, event): + pos = event.pos() + if self.isDrawing: + if self.isDrawRectangle or self.isDrawEllipse: + self.screenArea.setEndEditPoint(pos) + elif self.isDrawGraffiti: + self.screenArea.saveGraffitiPointF(pos) + elif self.isCapturing: + self.hasScreenShot = True + self.screenArea.setEndPoint(pos, remake=True) + elif self.isMoving: + self.screenArea.moveCenterAreaTo(pos) + elif self.isAdjusting: + self.screenArea.adjustCenterAreaBy(pos) + self.update() + if self.hasScreenShot: + self.setCursor(self.screenArea.getMouseShapeBy(pos)) + else: + self.setCursor(QtCore.Qt.CursorShape.CrossCursor) # 设置鼠标样式 十字 + + def mouseDoubleClickEvent(self, event): + if event.button() == QtCore.Qt.MouseButton.LeftButton: + if self.screenArea.isMousePosInCenterRectF(event.pos()): + self.save2Clipboard() + self.close() + + def keyPressEvent(self, QKeyEvent): + if QKeyEvent.key() == QtCore.Qt.Key.Key_Escape: + self.close() + if QKeyEvent.key() in (QtCore.Qt.Key.Key_Return, QtCore.Qt.Key.Key_Enter): # 大键盘、小键盘回车 + self.save2Clipboard() + self.close() + + def save2Clipboard(self): + '''将截图区域复制到剪贴板''' + if self.hasScreenShot: + mimData = QtCore.QMimeData() + mimData.setImageData(self.screenArea.centerPhysicalPixmap().toImage()) + QApplication.clipboard().setMimeData(mimData) + # self.screenArea.saveNightAreaImg() + self.close() + + def save2Local(self): + fileType = self.fileType_img + filePath, fileFormat = self.sys_selectSaveFilePath(self, fileType=fileType) + if filePath: + self.screenArea.centerPhysicalPixmap().save(filePath, quality=100) + self.close() + + def sys_getCurTime(self, fmt='%Y-%m-%d %H:%M:%S'): + '''获取字符串格式的当前时间''' + # return QtCore.QDateTime.currentDateTime().toString('yyyy-MM-dd hh:mm:ss') + return datetime.now().strftime(fmt) + + def sys_selectSaveFilePath(self, widget, title='选择文件保存路径', saveFileDir=None, + saveFileName='', defaultFileFmt='%Y%m%d%H%M%S', fileType=None): + '''选择文件保存路径 + title:选择窗口标题 + saveFileDir:指定保存目录 + saveFileName:默认保存文件名 + defaultFileFmt:不指定saveFileName时，自动以此格式的时间字符串命名文件 + fileType:可以选择的文件类型 + return:(所选的文件保存路径, 文件的类型) + ''' + options = QFileDialog.Option.ReadOnly + if saveFileName == '': + saveFileName = self.sys_getCurTime(defaultFileFmt) + if not saveFileDir: + saveFileDir = self.dir_lastAccess + saveFilePath = os.path.join(saveFileDir, saveFileName) + if not fileType: + fileType = self.fileType_all + filePath, fileFormat = QFileDialog.getSaveFileName(widget, title, saveFilePath, fileType, options=options) + if filePath: + self.dir_lastAccess = os.path.dirname(filePath) + return (filePath, fileFormat) + + diff --git a/icons/chinese.png b/icons/chinese.png new file mode 100644 index 0000000000000000000000000000000000000000..328e2fff73bd75188fa888aae45c8cb4ca844f57 GIT binary patch literal 2670 zcmds3dpMNa8eiXNFq0S>#3n;7<2t4rp_*~ViS0ULCNd%u2`QDzB>8F-2{XBM!5|C` zl1oUb+0`U!C!^sMDxwhWE~MPrU;FI;&mZSG|D5MpYyF=0{XJ{F@AIzTde(c!$7{$Q{jd@;ZttCXazC&H*#mVm%i z!uHbvg{X!HxJZEhj4$F1k3FcM;(>sgX8OAm8W?-q{d3u60IP7;M!Yo#1a1pC5{Cw% zxDvND-VkW-PN(yTfWTYfd5Mb!uEM=(x-Xg;pda<6TqmIjFY`@Sor=)7O^SL9BO%TvXYYOw8EP zwNZ~H%JRW)r|sWV+Kg15Zaj3~?=B9x8B0Tm#$@S7KX{}@(l0H!JZ`QDig{Da&d-5h z31!$t-mM5Np&S*5b8P^M@cHt11P{TD@_Hw20O7dw=>{r*1j6xc!lf`sxm9uW1px-G z-qTi{XbPYOF*iozC}8-qWHP~g@KvwhKLYpS`{tzN_3uv!{e>o8soz-oH}Ii}xO zS6u_>tPtcU2c{`vU=^(EnNO)~*O`}1DFt_E<$Zdob7{>6#y#Y&nFB3tDel%l=Ngab zVNiCK*l?Mba$H`$zQk6aGBkh^#8n3#^Mz9G#%go+EE#mM{7O}+l%5?sZ65AD;$jKf z8*LMcw7a`kH5nizAWyygZ@EfCfZ>EYn&`zPP#@Q1dY(S3)p{$?b=vfK%@h#iSgi9p zzMW*|*IHdsDvCFVSFt;CB?J5m z+v4aI2MnA7(Un^gxzp+=IE9SCa-)pB8Jw<-^OCYrBVhD_FcJR^3cVy6N>B$~3XJ&| zJN!&~;%v+84nxZD+6>9UM`&2g*OqCLgnzVf(z6tBfNXQ4QG{SbB`3WE{hw^XBDm4t z>rFGJH(D)InK)*q8p4I!cHYI64|36f)Rt z7B+?T_c>>z8t+vt{_Ud=WS98sNr#9%`b+I75|C^!65;YR5i*#xNJk#lZ#VC=HDmm$4AYzolL-e zrT$AP#2|F;{K>z=C3rRWFYHUmpl`Me3${2)V8^v?dp<=kao?FAXVb$9C-LjloxYlh z4}4?fqmW$p=d2!WLef*TUTAJWp3jg)*wcN;U8n@i?vGGVhVQdFie8~`K&N5qjZ6^- z&QxYo@1O~bfNPy#DJ!}jxN34}>E_n_;P-DmX5YMd^TnxiP#!WrSp(pHr;pAK@PxP2 z`XpCa=vD69WkL=b7w4&JJRUr-Tw8!Y!WW?7s$0zYp`_otT)ryNMoeI&TCQKwq1$rL zH#IedyWjx>BVfhb9Pe$qJ4$aXPU4yLB#Y_SNBGjX1^A<Gf2T;JWP6G0x{{Ql!fe{u2u@7$@eGH*{ikEY!gr?#e+j{w(m=@C3l zk%H^3w?LyNCvTtDrj@ME{cJlcCyHQgzhL-4gMvTZWTXRE{)UFZNX=Eu73nJ25;#}`rhO>V7zDUD?BMyJDqDr z58+wWDh6>_73Ck+V+cUDoo=}t5gon9_edXtV^=G3Fo-CL@2}j9MljazSw|8g+U)6P z1C0o_SVo39gF42+XZ6yKljG5BMA)tJhP8zk9>p}8G6U~2k6m$7{v2a(#r|z?!lsUN z3ftl1_e89oYI3i<%x+s9F|uPB!K%J4vgi>t^#j>6YZ$v*lOSyfF1Q_7I`i>k%!G`a zIlJ`)@?$?bb?J*!av#7a9tY~`HMmpJMG{X46l?jsc0}VHN6%-7GW}~yuBM)vEP@>= z{=4Ye8F+zJO{qR@Kd0@SBuRD+CH`QDHr|tFBa2~8FK?-ee+XfI2@NhS{56WaJZz={ zrM$gVS~tGxt*%*K*p}KJ4Fxv?bg#dbtW0h_V*v-A4-nVCPybG9b|m_sGc4SzuG^LPa|454UU_Vr+Xz>h`kp|k9F!mpBye-_qFr^~aq>??K8mXV literal 0 HcmV?d00001 diff --git a/icons/english.png b/icons/english.png new file mode 100644 index 0000000000000000000000000000000000000000..536c4a910ae6fc05040f4958477a34aeae891ea0 GIT binary patch literal 2888 zcmd5;i8mDb7yr&Mma#N5%}DiPvXmiDgp5=}mMIcr$x=kfl4!z=B{O!WFeKYNDKm_H z$nz`_M-3v&>y<2{JdN-u*^(CC^gsN5=e+MZ_j}L1pU*w#-g7_ae7|XSwpMcRJ#YYk z+-agYN#uKfnv{g-u5qcoCvuP*Br7veJNU~y05Z_i=BAERj}Jxei46;|0oWV>}?8p8~clS^b3LA)Q=xOY7Tlu zz=R90c^&bJt0uJKGU>xnvB$Qn}! zT@jrWKBfOXdoiG}(CmdQVyd$(8Lpqek;Zm<`O8(dY77USRgp|Ikj$90j#FR~A<`R0 zxxUg1^069qx1ij=PX7}S;AK-2u`GVK7HyZQqDN3X{wY8Q{(SX&W$U|N#S;Hy?}|pG zkkMJ7Yc38K?LcT$fH2><-%8d1Sok6LIj1nb{ z(3^5*>(`jVk5NZeQyEmjtS98vfFIx39M(%3JA@k7x;(X(fu=@AR;<5#3Bxk9Ty87v z!#CWqL$gz-V~OihCBQt3c<{p+MHLwEQCFjtLk{u>Yk z$YKR@pb&9_v2;jd1bC6im(K>0ej-NCuwCZuhOKV$&>mXGT!MBY` z-@6s;noAp;UFCJJ%i5dJQ^9r6y)D~+;%UHlXevM?r3MVBpJYrfs%C4BJJ*-iEYw&X zr;RbPg!uh{gpbz{&&iZ2fN4JV%yKPdJ;8j4o4{fa83zCq z%Oc{TLKLkkLqenyDT13R6btlZvD#RXn0CVv25KVC6G%xbeplbm42sFjnJzdCAWSca z{e>~8D5ZelM~RDy{Rx3wx1Ve=(veqCraW-%*shx&VQfFYDY4*u_wS;$A6J!C1lS@R4C_Rx0f2KwTY*i7$jw~@@-=yZ zGHc=;E-J5(8Z>m%aAuUG$h43pvR?a@i%>bNM;nAfk?FW7>IP7E3BCF=Sm_XkwRWIC&TmsJ2nEzs5?@ z0a1spKiOuCNsZPOL9IY7yzh=l3TmGeR#bfMl4v!eg{5UQF=TXGcG3QbH(vDhD08vT zj8*DP?+UBgGA8eMfeD8aqu64^R%bwZ;M7-9ZR(OxC*dWB`k;kw5Ff$X7bq)tqO~rX zl)22i>GCUwHD?^lTx{y|y>230L-NF|Sv5w_mb?VxaXh7T*gup=3X4IClWUzp2PWTnit&aXVpbU{{ zVyGj50C;_Dy}d|Q!eM%%usFCxLd2sIGMXE_uLeej!1?X90^^qFEb6n0buWNAuSn4R z$VqX4Ib>0_42)HvshhU{)azq*Xgxd{Vl#7)rn4Ik@o^s>wV-GFk=EV=QpxxA-%tc} zyPHL?6Zb@alOYeK?T}ru$b6_wvnNyxcg-}oJTMJP&+%qh_LvWlyt@6zO7XAeE_yqH ziVF$UBsKn_Qa>BqBQ%o{?uq;zr~vc*-sxWCp#fKAVeBg$cTvzB(vwGbhu4$@TQ7Jl zyo+FjTTg2Whx$V1?nWKhY(t50%}AsO@)SkVPqE2g*c|ja)Pna#600>|+di=&Z~81& zc=JOl(Zk6%&sb*!hocXGWv@Np;r_D-!|xkCJv}pT+hg&^TDjedWSPiDjbjGM-`gP8ff-zRxcksM+tgAjN+NR1o#?hL_#>DTQNSz=Oj#nI;>nExW&d&Wof z9!LaRVv^xN)aUqsr<3|#-?vxB_#^E7<%}iQnD;r~U@Ek;wombJ&Nac0YMUf(C53Vx z(xtD}bKC!oos|r)C`~|pD7?<#hULh6Pq>HB9kBq3 z7(B0a-{pQvz8bxJWPf0m#!@ppOj3&7dwpQk>wWfm zN|?C4V07Nj-;7*N4_sqHQSi&?>vLtxX1VD~WP;1B+p~rtyKz>T2k3_x)P|Qv%YQVF z9eTuQ%-v1w)-7V&a2%@K-<$<4wvCRI*ZUfg4?c1TJBPMhBC8LScp_S`w!V#lF zu`c3tkFSzyaQ*w{*AK?fw+zy(`Zv?Ypz?Q+!ULP@mflp-YD%#m_Qe}?9hAMP@*}H` z{(?0V^K@sY6wkD+ql5Jr?xn{c4~z$AzHIxtjtp%dY5nr4$|5I^l3->rySkZYk>nn} zDAC)1^wZHTr_f;4R;e!ClMs|leg~Ug3I*O3hT$y^fFLl~4RO~5*xW#eykju%^x_?4 e-Tw*Rf|uz1)S^WfMiTvdrwa*ZvLr!#SVxI-mFZoY&`iPR0=znj&c%2>_tT zpxe2jvh~{_D4?^@TU3AwD9Vj?2#7j%`~d(lhGA#p5zm_A`JWr!zscd5!HW*|@O4uk zpWe7(NAbMzwO71ddCpe>k#ncYRO21i<%#Q}tM5u0Mz{Jda%ejhNe;(@)OjS?k^~5I z$rx~m%tv?_C+_}HZ_^A6*vlwn)VM(4Zts<&*K`4Vjhb&VO9lUix(m;po}Rv~w0wZ) z5~1{2^Nw7VvO!B4*~l78rt7U2ARprBZilOYO4X1iCq%a|rrkL87S*y%7Hf4oX)gYt zk*NsT2d7CVj^{9#er>ruMx~5ykA`+$4;pU_1&vl2##4`=$ zX&A}Il|2@+r2#)q*f`_Xmb2z?%jDUZf~fwvs@c`^b$+aRR_^5tz3PqJ$%S8ZT0X>; z$6h9DNwoLX@V8R3Ji|?~IcDn)!rcm~#Yfp04{P3tf<6-LIg$N`MFt~-IlW?MOyBY4ANSg5LPfv5__XsPAwJRv+%3DDXN1kk4AwP*xQCOI1#Ul{cnJiBfxg_x z6BUKJO^%R&dBl*e`SpQAM%wNT6zFSRjW%4=O#zxmwzgXyb9Hr{cyz0y*ZdJk2e3tI zAJZ|Ey;<5IoL&9%GnsQV6xdbAa0Jdym(6v6Kv+8FiDlIAOWz&^aQpI_8lVr^-{0#D z1dVy-J9S3~-G+pN)zUjej_&fMKAvI8T)v{^>YOu!0x0P_< zJr55w-5*Ps9D)B7(;bHlg?UjSdS*!dUqwn>KxdC;?nI67E*EZzeO!Tu+fDV!Pk6#} z!UwFu;mfGLJ=T7_?7pKY!bpK@w(eJ{kh8jX`HO}Vch%QaIAyLjJB3A4dPLOp@Z)ZO zui_5epuai~|8vn)YyYh2l2JTkEhOGm9Ru%QcX_Rd*V?s<)5Qu>1>Ef=bBqfE9i*JC z96;xK_A#&su)9-}Vuz;yVo%%tlYqdPiT31{0Ss*8>!YIxAPTR8q^ybnExP`!0D?hL zua8X;hQPs{JkB!#I3#+%KHURATv%9nO@RZ_T~6RLNH9&JqpVICUamN%SJHor-JZR)N&bWy5Ev*3*BNkVpB_xZV0NfPmo!r25=s-c!pbL@ z?4g>SMx@-t^auicLCU{jmMQ7%ne3w=zo?zv-s%36w!6R*b|SkPQrT7itg{E4r}Zqs zf`{RkA%CcXQ#pElJViIs7K-AGThF*Vl5*EJv%SbE^6J-WAMnTwM15GysT*!+nN*V7 zy!2)AXAE^lv%FWx`Uy|1tf;xQI8dT=M-eoPj*Za#v%J4%lr%^5UeB`cRDAOG zqdrBMd)!AH5o%?gmt~)CAi^lKVmsA`cB|Nx`91qDbLM>No-)8Wy#-PNs}o``s6J`~-#Adab3o zNPoUOG|ZRWM6nS$hZzRSWCucdt@rpP(JRszn*Ja%ov zg$8}&HvX~OFq%Iv>GGg$l!7FL<_VB^8ANnYtpAPJv_Lv-wN8`Omz5f=g<4$kUhh#r zvu8qK^aJjsM!}=Z;wPct` zoGUI}$&SCm`t>UQ;+b&NxKk3nf&Kb2ERtgCnH&A>LgslNZL+>h`WhvbE#<%DgT== zaE<0@`RrI&H$VFp>Z$mHEZ)_latMB-eY{YB0ZpIDFA_;xUY5(Zn%R6(pE%#3rvbit zS*_9BQP$}<{Oo+RaI0D>_K81OUqa#8?^&ce3K~2m@x789bko6!lI7*bQ`PzpC$Q^c zt=MH-p5iK(C>G5Ie1A9NJu^AC=i~E)ih{!ivbOMImceZ&2;8h37f5WOIZ2Td_xoq# zC10q3!Zr<}U7~g+4lAoPAGtT!b_VaU-jXiymZ%0oq!A`SLdnztH)J@;*knM4781WBWnywjOFyzyu}##g28Q== z)S0~pGoheNLT)Z4m{j@C^Vp1eOI-S7GcoO3=$g3Pnh}QcE^?4l^YntoOwp8G<^EGTmQ%&`ZF%(PVXP# zOR@RTcRbKfgPife&fPy);subA8(f@;Dxf&WWX!Q3a5mtOa+e1{Ox|ceVB~40{(l(V@VUzX4L5ReS&d literal 0 HcmV?d00001 diff --git a/icons/folder-plus.png b/icons/folder-plus.png new file mode 100644 index 0000000000000000000000000000000000000000..01ce6c10b0ed3e3975edbebbc8e886f846fabe8d GIT binary patch literal 2598 zcmd5;TR4=98Xo%bqxg*^q5hdh2d9b_i$Q({GZGeqK}`qelv5g0Y12^6P)y^LLgmm& zh8d?sv7AE*GY(s_gfuxs%*tV9t=TvGe(#ID_Qm(T7w`MseDC`_-^X%wcG#q_O#y{M zZ6Xl~ZW3(&SAnvUUP9sKNkHnHn}ZFC`&LVYLdpL|A|PZsbvE~yr=}TXKcX+cxSit7 z$!NLIrq6n-GRR8X+P6y9%_zk0GoEtF`p4X((DSD7KK%L>6kvrbYmk+OmT#jNW#({1 zf&?t!c=(wV7z_*|2gArmY*5H9`8y$}0f;beFT??mKj(h-LwnSJPQI79K&R8SShI_Z zizf?L_Gi`0lhtsq=T}!(cQy0%kJD;LT%(TOk4>APTUhZLTCuKn?6tME@J@cLwxaOi zkXB~E%3Cg<<)N;gt!Tv4s^4&YK)lx3*;#GqiAty=H8`=O@s-?ZWqQ4;HRpgQg9XoQ z8&GfJ>$|)U6B{`4;2AAb^@b~Q-(SlNef=(~IxVPnZxKZmd)z1s*k#tc_db&jOx#MBj~9_qcIh*3A@Fd}K)xF~F(@_vF}>U)vAddr zP8=@gv!4rf$EUnY6!;gFqMBc^3scGEGGi-Eh7=sn&%0O$cw$HMt0nSP$OWBz86Mr* zCHdpr9Jlt+LC3gZxAB4H3+2LKaroyd7Hqi>Ojc&<)yxNmHk~>fDbD}}p>-|eo`=E4 z2LJ-JS5nC^3$mX?11eHpFN7bJOPVcCXJCj@-nhN-1Ejr-&9WYcIeEwZH)A(>q`r)sRBdb(VAzicMSrx%KIrq2CU|#9A2f{I5N1jK<}cCXB`Pr_kC~Pwd8(Ek*YZ$ zoplW3`XU)-Ht}uHa_y!s_S^!H9KJ1j_q!d@1s_ghn0{fzkKo!puHcx2Fdl!CX*};9 z1NL6KL@TWu>aY*=fPc^q;+bmeH)w3!hRm^|j&mSmt1P=uK;kSNX^35MReH_{RVhSK zi+lSL*4jrgqYATeKXkh>Gw{ie!?V3ybnwp)uAPbu-oZ#rO8=FDE~AIpLY;(Qz0Fd9 zyqa7BOOpD0okqHiiZ$Cca{ujM0K)lTZ|wfx)5}V`uEv?C!?|I6-vM#ZDsA}Aac2>} z>DvdWFy~~9!5OpSn1`iF&(&Z?bah>)Y@J=oIpvNJt$>1Lubc3K(G!z=Ei?8+E{Z|+ zP2p`bl=m?+H}0Pi_oPSYt+2=Z?JSL-@F%8~178VkppY7|SH*XxQv@4T@Ap zptNAIy}tCjOQ{|#IPTkTTc(?(k#&6q0Ac@W#a96k?(Fys9CxTtU0Yv!+Mcvy6CT93 z3x&pu-PVTjS}ASgXr{BYKfmq5JU)?a$~{ffr>ORe=+7s1(>Z(NL4_hX@(hKzF*ae z>#%uTmSZw|2w8gke<0qO=RGOa&Cq7haUO#XBAyMHFBdOKUv)>Ls=LkhFQ24RwVM;7 z*j9pL{{3=Gn>87Lcir|TSDMP??+t#2)XOkaT?GG_AR5(b&A`Z(lJEPgVs)`?mvnt8 zmox7*a?bIr3ck$$>AqZATAC_3Sfr7X>D9%#xw-j2{)mnE{3_WHDonn;)n88<>`k)x zK|@f;3nmMx!p6fT?S0|uz~4zfMB{P|Zz<_~#%joFFd9Uz$)!38qEF;B4#`bXDkDD1 zDBySAp^%6#J=tHHA1B1iNCCY2M9n6&t8=SY40}iI$Xq0a<8+1~-TQi(1Dj2Cq!90z zi5;vjSi6)H*z5ejW@)L(727R|a_2D^M;|mhtTYK2Gbs-Eu#{_SJz|*zkXncwRn>ti z_`cPpoHkv{grm;s_gEFoTq{#FJG`U|IH^9gRV}MVbx%#Dk!qr^!T0x~hz(bIef8WC zH@`=tRZjIzt;&!o(5@o}DKlE17&)2~nZ?xkirBmHLT=>H;RV~(N=*6PvhB{<a2i^f(p9I4MBG$a7bK9SV6y?0w6YJW1`8>~uBBp0Fgm kE!vum@e6SKFNc?9_7=&6MRodPC66D9Wamua+MHng1 0: + self.imagePaths = selectedFiles + self.screenShot = None # discard screenshot temp image + self.updateProgressBar(len(selectedFiles), 0) + + def screenShotSlot(self): + ''' + 选定图像文件和截图的转换过程只能同时进行一个 + 截图只能同时转换一个 + ''' + self.screenShotWg.start() + if self.screenShotWg.captureImage: + self.screenShot = self.screenShotWg.captureImage + self.imagePaths.clear() # discard openfile temp list + self.updateProgressBar(1, 0) + + def startSlot(self, lang): + if self.screenShot: # for screenShot + img_name = 'screenshot_' + time.strftime("%Y%m%d%H%M%S", time.localtime()) + image = QImageToCvMat(self.screenShot) + self.predictAndSave(image, img_name, lang) + # update Progress Bar + self.updateProgressBar(1, 1) + QtWidgets.QMessageBox.information(self, + u'Information', "文档提取完成") + elif len(self.imagePaths) > 0 : # for image file selection + self.output_dir = os.path.join( + os.path.dirname(self.imagePaths[0]), "output") # output_dir shold be same as imagepath + os.makedirs(self.output_dir, exist_ok=True) + for i, image_file in enumerate(self.imagePaths): + if os.path.basename(image_file)[-3:] in ['pdf']: + import fitz + from PIL import Image + imgs = [] + with fitz.open(image_file) as pdf: + for pg in range(0, pdf.pageCount): + page = pdf[pg] + mat = fitz.Matrix(2, 2) + pm = page.getPixmap(matrix=mat, alpha=False) + + # if width or height > 2000 pixels, don't enlarge the image + if pm.width > 2000 or pm.height > 2000: + pm = page.getPixmap(matrix=fitz.Matrix(1, 1), alpha=False) + + img = Image.frombytes("RGB", [pm.width, pm.height], pm.samples) + img = cv2.cvtColor(np.array(img), cv2.COLOR_RGB2BGR) + imgs.append(img) + + else: + img = cv2.imread(image_file) + if img is None: + print("error in loading image:{}".format(image_file)) + continue + imgs = [img] + + img_name = os.path.basename(image_file).split('.')[0] + os.makedirs(os.path.join(self.output_dir, img_name), exist_ok=True) + self.predictAndSave(imgs, img_name, lang) + + # update Progress Bar + self.updateProgressBar(len(self.imagePaths), i+1) + QtWidgets.QMessageBox.information(self, + u'Information', "文档提取完成") + else: + print('empty input') + + def predictAndSave(self, imgs, img_name, lang): + all_res = [] + for index, img in enumerate(imgs): + if lang == 'EN': + res, time_dict = self.structure_sys_en(img) + elif lang == 'CN': + res, time_dict = self.structure_sys_cn(img) + + # save output + save_structure_res(res, self.output_dir, img_name) + draw_img = draw_structure_result(img, res, self.vis_font_path) + img_save_path = os.path.join(self.output_dir, img_name, 'show_{}.jpg'.format(index)) + if res != []: + cv2.imwrite(img_save_path, draw_img) + + # recovery + h, w, _ = img.shape + res = sorted_layout_boxes(res, w) + all_res += res + + try: + convert_info_docx(img, all_res, self.output_dir, img_name, self.save_pdf) + except Exception as ex: + QtWidgets.QMessageBox.information(self, + u'Information', "error in layout recovery image:{}, err msg: {}".format( + img_name, ex)) + + print('result save to {}'.format(self.output_dir)) + + def showResultSlot(self): + if os.path.exists(self.output_dir): + if platform.system() == 'Windows': + os.startfile(self.output_dir) + else: + os.system('open ' + os.path.normpath(self.lastOpenDir)) + else: + QtWidgets.QMessageBox.information(self, + u'Information', "输出文件不存在") + + def updateProgressBar(self, loaded, finished): + self.pb.setText( + self.pb_text.format(loaded, finished)) + + +def main(): + app = QtWidgets.QApplication(sys.argv) + + window = APP_Image2Doc() # 创建对象 + window.show() # 全屏显示窗口 + + QtWidgets.QApplication.processEvents() + sys.exit(app.exec()) + + +if __name__ == "__main__": + main() \ No newline at end of file From 1a0a75e3fa896cf3c095e4146a54acef7223657e Mon Sep 17 00:00:00 2001 From: Leif <4603009@qq.com> Date: Wed, 24 Aug 2022 16:34:36 +0800 Subject: [PATCH 11/14] Add pdf2word exe Add pdf2word exe --- image2doc.py | 349 -------------- .../pdf2word/icons}/chinese.png | Bin .../pdf2word/icons}/english.png | Bin .../pdf2word/icons}/folder-open.png | Bin .../pdf2word/icons}/folder-plus.png | Bin .../pdf2word/pdf2word.md | 17 +- ppstructure/pdf2word/pdf2word.py | 441 ++++++++++++++++++ 7 files changed, 450 insertions(+), 357 deletions(-) delete mode 100644 image2doc.py rename {icons => ppstructure/pdf2word/icons}/chinese.png (100%) rename {icons => ppstructure/pdf2word/icons}/english.png (100%) rename {icons => ppstructure/pdf2word/icons}/folder-open.png (100%) rename {icons => ppstructure/pdf2word/icons}/folder-plus.png (100%) rename PDF2WORD.md => ppstructure/pdf2word/pdf2word.md (74%) create mode 100644 ppstructure/pdf2word/pdf2word.py diff --git a/image2doc.py b/image2doc.py deleted file mode 100644 index 700126e024..0000000000 --- a/image2doc.py +++ /dev/null @@ -1,349 +0,0 @@ -import sys -import tarfile -import os -import time -import functools -import cv2 -import platform -import numpy as np -from qtpy import QtWidgets -from qtpy.QtGui import QImage, QPixmap, QIcon - -from ppstructure.predict_system import StructureSystem, save_structure_res -from ppstructure.utility import parse_args, draw_structure_result -from ppocr.utils.network import download_with_progressbar -from ppstructure.recovery.recovery_to_doc import sorted_layout_boxes, convert_info_docx -from ScreenShotWidget import ScreenShotWidget - -__APPNAME__ = "Image2Doc" -__VERSION__ = "0.0.2" -here = os.path.dirname(os.path.abspath(__file__)) -URLs_EN = { - # 下载超英文轻量级PP-OCRv3模型的检测模型并解压 - "en_PP-OCRv3_det_infer": "https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_det_infer.tar", - # 下载英文轻量级PP-OCRv3模型的识别模型并解压 - "en_PP-OCRv3_rec_infer": "https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_infer.tar", - # 下载超轻量级英文表格英文模型并解压 - "en_ppstructure_mobile_v2.0_SLANet_infer": "https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/en_ppstructure_mobile_v2.0_SLANet_infer.tar", - # 英文版面分析模型 - "picodet_lcnet_x1_0_fgd_layout_infer": "https://paddleocr.bj.bcebos.com/ppstructure/models/layout/picodet_lcnet_x1_0_fgd_layout_infer.tar", -} -DICT_EN = { - "rec_char_dict_path": "en_dict.txt", - "layout_dict_path": "layout_publaynet_dict.txt", -} - -URLs_CN = { - # 下载超中文轻量级PP-OCRv3模型的检测模型并解压 - "cn_PP-OCRv3_det_infer": "https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar", - # 下载中文轻量级PP-OCRv3模型的识别模型并解压 - "cn_PP-OCRv3_rec_infer": "https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar", - # 下载超轻量级英文表格英文模型并解压 - "cn_ppstructure_mobile_v2.0_SLANet_infer": "https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/en_ppstructure_mobile_v2.0_SLANet_infer.tar", - # 中文版面分析模型 - "picodet_lcnet_x1_0_fgd_layout_cdla_infer": "https://paddleocr.bj.bcebos.com/ppstructure/models/layout/picodet_lcnet_x1_0_fgd_layout_cdla_infer.tar", -} -DICT_CN = { - "rec_char_dict_path": "ppocr_keys_v1.txt", - "layout_dict_path": "layout_cdla_dict.txt", -} - - -def QImageToCvMat(incomingImage): - ''' - Converts a QImage into an opencv MAT format - ''' - - incomingImage = incomingImage.convertToFormat(QImage.Format.Format_RGBA8888) - - width = incomingImage.width() - height = incomingImage.height() - - ptr = incomingImage.bits() - ptr.setsize(height * width * 4) - arr = np.frombuffer(ptr, np.uint8).reshape((height, width, 4)) - return arr - - -class APP_Image2Doc(QtWidgets.QWidget): - def __init__(self): - super(QtWidgets.QWidget, self).__init__() - self.pb = None # 进度条 - self.pb_text = "已载入: {} / 已转换: {}" - self.imagePaths = [] - # self.resultPath = os.path.join(here, "output") - self.screenShotWg = ScreenShotWidget() - self.screenShot = None - self.save_pdf = False - - self.vis_font_path = os.path.join(here, - "doc", "fonts", "simfang.ttf") - - # 初始化界面 - self.setupUi() - - # 下载模型 - self.downloadModels(URLs_EN) - self.downloadModels(URLs_CN) - - self.structure_sys_en = self.initPredictor('EN') - self.structure_sys_cn = self.initPredictor('CN') - - def setupUi(self): - self.setObjectName("MainWindow") - self.setWindowTitle(__APPNAME__ + " " + __VERSION__) - - layout = QtWidgets.QGridLayout() - - openFileButton = QtWidgets.QPushButton("打开文件") - openFileButton.setIcon(QIcon(QPixmap("./icons/folder-plus.png"))) - layout.addWidget(openFileButton, 0, 0, 1, 1) - openFileButton.clicked.connect(self.openFileSlot) - - # screenShotButton = QtWidgets.QPushButton("截图识别") - # layout.addWidget(screenShotButton, 0, 1, 1, 1) - # screenShotButton.clicked.connect(self.screenShotSlot) - # screenShotButton.setEnabled(False) # temporarily disenble - - startCNShotButton = QtWidgets.QPushButton("中文转换") - startCNShotButton.setIcon(QIcon(QPixmap("./icons/chinese.png"))) - layout.addWidget(startCNShotButton, 0, 1, 1, 1) - startCNShotButton.clicked.connect( - functools.partial(self.startSlot, 'CN')) - - startENButton = QtWidgets.QPushButton("英文转换") - startENButton.setIcon(QIcon(QPixmap("./icons/english.png"))) - layout.addWidget(startENButton, 0, 2, 1, 1) - startENButton.clicked.connect( - functools.partial(self.startSlot, 'EN')) - - showResultButton = QtWidgets.QPushButton("显示结果") - showResultButton.setIcon(QIcon(QPixmap("./icons/folder-open.png"))) - layout.addWidget(showResultButton, 0, 3, 1, 1) - showResultButton.clicked.connect(self.showResultSlot) - - self.pb = QtWidgets.QLabel( - self.pb_text.format(0, 0)) - layout.addWidget(self.pb, 1, 0, 1, 4) - - self.setLayout(layout) - - def downloadModels(self, URLs): - # using custom model - tar_file_name_list = [ - 'inference.pdiparams', - 'inference.pdiparams.info', - 'inference.pdmodel', - 'model.pdiparams', - 'model.pdiparams.info', - 'model.pdmodel' - ] - model_path = os.path.join(here, 'inference') - os.makedirs(model_path, exist_ok=True) - - # download and unzip models - for name in URLs.keys(): - url = URLs[name] - print("Try downloading file: {}".format(url)) - tarname = url.split('/')[-1] - tarpath = os.path.join(model_path, tarname) - if os.path.exists(tarpath): - print("File have already exist. skip") - else: - try: - download_with_progressbar(url, tarpath) - except Exception as e: - print("Error occurred when downloading file, error message:") - print(e) - - # unzip model tar - try: - with tarfile.open(tarpath, 'r') as tarObj: - storage_dir = os.path.join(model_path, name) - os.makedirs(storage_dir, exist_ok=True) - for member in tarObj.getmembers(): - filename = None - for tar_file_name in tar_file_name_list: - if tar_file_name in member.name: - filename = tar_file_name - if filename is None: - continue - file = tarObj.extractfile(member) - with open( - os.path.join(storage_dir, filename), - 'wb') as f: - f.write(file.read()) - except Exception as e: - print("Error occurred when unziping file, error message:") - print(e) - - def initPredictor(self, lang='EN'): - # init predictor args - args = parse_args() - args.table_max_len = 488 - args.ocr = True - args.recovery = True - args.save_pdf = self.save_pdf - args.table_char_dict_path = os.path.join(here, - "ppocr", "utils", "dict", "table_structure_dict.txt") - if lang == 'EN': - args.det_model_dir = os.path.join(here, # 此处从这里找到模型存放位置 - "inference", "en_PP-OCRv3_det_infer") - args.rec_model_dir = os.path.join(here, - "inference", "en_PP-OCRv3_rec_infer") - args.table_model_dir = os.path.join(here, - "inference", "en_ppstructure_mobile_v2.0_SLANet_infer") - args.output = os.path.join(here, "output") # 结果保存路径 - args.layout_model_dir = os.path.join(here, - "inference", "picodet_lcnet_x1_0_fgd_layout_infer") - lang_dict = DICT_EN - elif lang == 'CN': - args.det_model_dir = os.path.join(here, # 此处从这里找到模型存放位置 - "inference", "cn_PP-OCRv3_det_infer") - args.rec_model_dir = os.path.join(here, - "inference", "cn_PP-OCRv3_rec_infer") - args.table_model_dir = os.path.join(here, - "inference", "cn_ppstructure_mobile_v2.0_SLANet_infer") - args.output = os.path.join(here, "output") # 结果保存路径 - args.layout_model_dir = os.path.join(here, - "inference", "picodet_lcnet_x1_0_fgd_layout_cdla_infer") - lang_dict = DICT_CN - else: - raise ValueError("Unsupported language") - args.rec_char_dict_path = os.path.join(here, - "ppocr", "utils", - lang_dict['rec_char_dict_path']) - args.layout_dict_path = os.path.join(here, - "ppocr", "utils", "dict", "layout_dict", - lang_dict['layout_dict_path']) - # init predictor - return StructureSystem(args) - - def openFileSlot(self): - ''' - 可以多选图像文件 - ''' - selectedFiles = QtWidgets.QFileDialog.getOpenFileNames(self, - "多文件选择", "/", "图片文件 (*.png *.jpeg *.jpg *.bmp *.pdf)")[0] - if len(selectedFiles) > 0: - self.imagePaths = selectedFiles - self.screenShot = None # discard screenshot temp image - self.updateProgressBar(len(selectedFiles), 0) - - def screenShotSlot(self): - ''' - 选定图像文件和截图的转换过程只能同时进行一个 - 截图只能同时转换一个 - ''' - self.screenShotWg.start() - if self.screenShotWg.captureImage: - self.screenShot = self.screenShotWg.captureImage - self.imagePaths.clear() # discard openfile temp list - self.updateProgressBar(1, 0) - - def startSlot(self, lang): - if self.screenShot: # for screenShot - img_name = 'screenshot_' + time.strftime("%Y%m%d%H%M%S", time.localtime()) - image = QImageToCvMat(self.screenShot) - self.predictAndSave(image, img_name, lang) - # update Progress Bar - self.updateProgressBar(1, 1) - QtWidgets.QMessageBox.information(self, - u'Information', "文档提取完成") - elif len(self.imagePaths) > 0 : # for image file selection - self.output_dir = os.path.join( - os.path.dirname(self.imagePaths[0]), "output") # output_dir shold be same as imagepath - os.makedirs(self.output_dir, exist_ok=True) - for i, image_file in enumerate(self.imagePaths): - if os.path.basename(image_file)[-3:] in ['pdf']: - import fitz - from PIL import Image - imgs = [] - with fitz.open(image_file) as pdf: - for pg in range(0, pdf.pageCount): - page = pdf[pg] - mat = fitz.Matrix(2, 2) - pm = page.getPixmap(matrix=mat, alpha=False) - - # if width or height > 2000 pixels, don't enlarge the image - if pm.width > 2000 or pm.height > 2000: - pm = page.getPixmap(matrix=fitz.Matrix(1, 1), alpha=False) - - img = Image.frombytes("RGB", [pm.width, pm.height], pm.samples) - img = cv2.cvtColor(np.array(img), cv2.COLOR_RGB2BGR) - imgs.append(img) - - else: - img = cv2.imread(image_file) - if img is None: - print("error in loading image:{}".format(image_file)) - continue - imgs = [img] - - img_name = os.path.basename(image_file).split('.')[0] - os.makedirs(os.path.join(self.output_dir, img_name), exist_ok=True) - self.predictAndSave(imgs, img_name, lang) - - # update Progress Bar - self.updateProgressBar(len(self.imagePaths), i+1) - QtWidgets.QMessageBox.information(self, - u'Information', "文档提取完成") - else: - print('empty input') - - def predictAndSave(self, imgs, img_name, lang): - all_res = [] - for index, img in enumerate(imgs): - if lang == 'EN': - res, time_dict = self.structure_sys_en(img) - elif lang == 'CN': - res, time_dict = self.structure_sys_cn(img) - - # save output - save_structure_res(res, self.output_dir, img_name) - draw_img = draw_structure_result(img, res, self.vis_font_path) - img_save_path = os.path.join(self.output_dir, img_name, 'show_{}.jpg'.format(index)) - if res != []: - cv2.imwrite(img_save_path, draw_img) - - # recovery - h, w, _ = img.shape - res = sorted_layout_boxes(res, w) - all_res += res - - try: - convert_info_docx(img, all_res, self.output_dir, img_name, self.save_pdf) - except Exception as ex: - QtWidgets.QMessageBox.information(self, - u'Information', "error in layout recovery image:{}, err msg: {}".format( - img_name, ex)) - - print('result save to {}'.format(self.output_dir)) - - def showResultSlot(self): - if os.path.exists(self.output_dir): - if platform.system() == 'Windows': - os.startfile(self.output_dir) - else: - os.system('open ' + os.path.normpath(self.lastOpenDir)) - else: - QtWidgets.QMessageBox.information(self, - u'Information', "输出文件不存在") - - def updateProgressBar(self, loaded, finished): - self.pb.setText( - self.pb_text.format(loaded, finished)) - - -def main(): - app = QtWidgets.QApplication(sys.argv) - - window = APP_Image2Doc() # 创建对象 - window.show() # 全屏显示窗口 - - QtWidgets.QApplication.processEvents() - sys.exit(app.exec()) - - -if __name__ == "__main__": - main() \ No newline at end of file diff --git a/icons/chinese.png b/ppstructure/pdf2word/icons/chinese.png similarity index 100% rename from icons/chinese.png rename to ppstructure/pdf2word/icons/chinese.png diff --git a/icons/english.png b/ppstructure/pdf2word/icons/english.png similarity index 100% rename from icons/english.png rename to ppstructure/pdf2word/icons/english.png diff --git a/icons/folder-open.png b/ppstructure/pdf2word/icons/folder-open.png similarity index 100% rename from icons/folder-open.png rename to ppstructure/pdf2word/icons/folder-open.png diff --git a/icons/folder-plus.png b/ppstructure/pdf2word/icons/folder-plus.png similarity index 100% rename from icons/folder-plus.png rename to ppstructure/pdf2word/icons/folder-plus.png diff --git a/PDF2WORD.md b/ppstructure/pdf2word/pdf2word.md similarity index 74% rename from PDF2WORD.md rename to ppstructure/pdf2word/pdf2word.md index 382a0febee..8d69d60748 100644 --- a/PDF2WORD.md +++ b/ppstructure/pdf2word/pdf2word.md @@ -1,11 +1,12 @@ # PDF2WORD -PDF2WORD是PaddleOCR社区开发者@whj 基于PP-Structure智能文档分析系统实现的PDF转换word应用程序，提供可直接安装的exe，方便windows用户运行 +PDF2WORD是PaddleOCR社区开发者@whj 基于PP-Structure智能文档分析模型实现的PDF转换Word应用程序，提供可直接安装的exe，方便windows用户运行
- +
+ ## 1.使用 ### 应用程序 @@ -16,17 +17,15 @@ PDF2WORD是PaddleOCR社区开发者@whj 基于PP-Structure智能文档分析系 ### 脚本运行 -首次运行需要将 +首次运行需要将切换路径到 `/ppstructure/pdf2word` ，然后运行代码 ``` python pdf2word.py ``` - - ## 2.自行打包 -PDF2WORD应用程序通过[QPT](https://github.com/QPT-Family/QPT)工具打包实现，若您修改了界面代码需要重新打包，请在 `ppstructure` 文件夹下运行下方指令 +PDF2WORD应用程序通过[QPT](https://github.com/QPT-Family/QPT)工具打包实现，若您修改了界面代码需要重新打包，请在 `PaddleOCR` 文件夹下运行下方指令 ``` cd ./ @@ -34,9 +33,11 @@ mv ./ppstructure/pdf2word .. -r python GenEXE.py ``` - - ## 3.软件下载 如需获取已打包程序，可以扫描下方二维码，关注公众号填写问卷后，加入PaddleOCR官方交流群免费获取20G OCR学习大礼包，内含OCR场景应用集合（包含数码管、液晶屏、车牌、高精度SVTR模型等7个垂类模型）、《动手学OCR》电子书、课程回放视频、前沿论文等重磅资料 +
+ +
+ diff --git a/ppstructure/pdf2word/pdf2word.py b/ppstructure/pdf2word/pdf2word.py new file mode 100644 index 0000000000..add8a6f405 --- /dev/null +++ b/ppstructure/pdf2word/pdf2word.py @@ -0,0 +1,441 @@ +import sys +import tarfile +import os +import time +import datetime +import functools +import cv2 +import platform +import numpy as np +from qtpy.QtWidgets import QApplication, QWidget, QPushButton, QProgressBar, \ + QGridLayout, QMessageBox, QLabel, QFileDialog +from qtpy.QtCore import Signal, QThread, QObject +from qtpy.QtGui import QImage, QPixmap, QIcon + +file = os.path.dirname(os.path.abspath(__file__)) +root = os.path.abspath(os.path.join(file, '../../')) +sys.path.append(file) +sys.path.insert(0, root) + +from ppstructure.predict_system import StructureSystem, save_structure_res +from ppstructure.utility import parse_args, draw_structure_result +from ppocr.utils.network import download_with_progressbar +from ppstructure.recovery.recovery_to_doc import sorted_layout_boxes, convert_info_docx +from ScreenShotWidget import ScreenShotWidget + +__APPNAME__ = "pdf2word" +__VERSION__ = "0.1.1" + +URLs_EN = { + # 下载超英文轻量级PP-OCRv3模型的检测模型并解压 + "en_PP-OCRv3_det_infer": "https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_det_infer.tar", + # 下载英文轻量级PP-OCRv3模型的识别模型并解压 + "en_PP-OCRv3_rec_infer": "https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_infer.tar", + # 下载超轻量级英文表格英文模型并解压 + "en_ppstructure_mobile_v2.0_SLANet_infer": "https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/en_ppstructure_mobile_v2.0_SLANet_infer.tar", + # 英文版面分析模型 + "picodet_lcnet_x1_0_fgd_layout_infer": "https://paddleocr.bj.bcebos.com/ppstructure/models/layout/picodet_lcnet_x1_0_fgd_layout_infer.tar", +} +DICT_EN = { + "rec_char_dict_path": "en_dict.txt", + "layout_dict_path": "layout_publaynet_dict.txt", +} + +URLs_CN = { + # 下载超中文轻量级PP-OCRv3模型的检测模型并解压 + "cn_PP-OCRv3_det_infer": "https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar", + # 下载中文轻量级PP-OCRv3模型的识别模型并解压 + "cn_PP-OCRv3_rec_infer": "https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar", + # 下载超轻量级英文表格英文模型并解压 + "cn_ppstructure_mobile_v2.0_SLANet_infer": "https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/en_ppstructure_mobile_v2.0_SLANet_infer.tar", + # 中文版面分析模型 + "picodet_lcnet_x1_0_fgd_layout_cdla_infer": "https://paddleocr.bj.bcebos.com/ppstructure/models/layout/picodet_lcnet_x1_0_fgd_layout_cdla_infer.tar", +} +DICT_CN = { + "rec_char_dict_path": "ppocr_keys_v1.txt", + "layout_dict_path": "layout_cdla_dict.txt", +} + + + +def QImageToCvMat(incomingImage) -> np.array: + ''' + Converts a QImage into an opencv MAT format + ''' + + incomingImage = incomingImage.convertToFormat(QImage.Format.Format_RGBA8888) + + width = incomingImage.width() + height = incomingImage.height() + + ptr = incomingImage.bits() + ptr.setsize(height * width * 4) + arr = np.frombuffer(ptr, np.uint8).reshape((height, width, 4)) + return arr + + +def readImage(image_file) -> list: + if os.path.basename(image_file)[-3:] in ['pdf']: + import fitz + from PIL import Image + imgs = [] + with fitz.open(image_file) as pdf: + for pg in range(0, pdf.pageCount): + page = pdf[pg] + mat = fitz.Matrix(2, 2) + pm = page.getPixmap(matrix=mat, alpha=False) + + # if width or height > 2000 pixels, don't enlarge the image + if pm.width > 2000 or pm.height > 2000: + pm = page.getPixmap(matrix=fitz.Matrix(1, 1), alpha=False) + + img = Image.frombytes("RGB", [pm.width, pm.height], pm.samples) + img = cv2.cvtColor(np.array(img), cv2.COLOR_RGB2BGR) + imgs.append(img) + else: + img = cv2.imread(image_file, cv2.IMREAD_COLOR) + if img is not None: + imgs = [img] + + return imgs + + +class Worker(QThread): + progressBarValue = Signal(int) + endsignal = Signal() + loopFlag = True + + def __init__(self, predictors, save_pdf, vis_font_path): + super(Worker, self).__init__() + self.predictors = predictors + self.save_pdf = save_pdf + self.vis_font_path = vis_font_path + self.lang = 'EN' + self.imagePaths = [] + self.outputDir = None + self.setStackSize(1024*1024) + + def setImagePath(self, imagePaths): + self.imagePaths = imagePaths + + def setLang(self, lang): + self.lang = lang + + def setOutputDir(self, outputDir): + self.outputDir = outputDir + + def predictAndSave(self, imgs, img_name): + all_res = [] + for index, img in enumerate(imgs): + res, time_dict = self.predictors[self.lang](img) + + # save output + save_structure_res(res, self.outputDir, img_name) + draw_img = draw_structure_result(img, res, self.vis_font_path) + img_save_path = os.path.join(self.outputDir, img_name, 'show_{}.jpg'.format(index)) + if res != []: + cv2.imwrite(img_save_path, draw_img) + + # recovery + h, w, _ = img.shape + res = sorted_layout_boxes(res, w) + all_res += res + + try: + convert_info_docx(img, all_res, self.outputDir, img_name, self.save_pdf) + except Exception as ex: + print(self, + "error in layout recovery image:{}, err msg: {}".format( + img_name, ex)) + + print('result save to {}'.format(self.outputDir)) + + def run(self): + try: + findex = 0 + os.makedirs(self.outputDir, exist_ok=True) + for i, image_file in enumerate(self.imagePaths): + if self.loopFlag == True: + imgs = readImage(image_file) + if len(imgs) == 0: + continue + img_name = os.path.basename(image_file).split('.')[0] + os.makedirs(os.path.join(self.outputDir, img_name), exist_ok=True) + self.predictAndSave(imgs, img_name) + findex += 1 + self.progressBarValue.emit(findex) + else: + break + self.endsignal.emit() + self.exec() + except Exception as e: + print(e) + raise + + +class APP_Image2Doc(QWidget): + def __init__(self): + super().__init__() + self.setFixedHeight(90) + self.setFixedWidth(400) + + # settings + self.imagePaths = [] + self.screenShotWg = ScreenShotWidget() + self.screenShot = None + self.save_pdf = False + self.output_dir = None + self.vis_font_path = os.path.join(root, + "doc", "fonts", "simfang.ttf") + + # ProgressBar + self.pb = QProgressBar() + self.pb.setRange(0, 100) + self.pb.setValue(0) + + # 初始化界面 + self.setupUi() + + # 下载模型 + self.downloadModels(URLs_EN) + self.downloadModels(URLs_CN) + + # 初始化模型 + predictors = { + 'EN': self.initPredictor('EN'), + 'CN': self.initPredictor('CN'), + } + + # 设置工作进程 + self._thread = Worker(predictors, self.save_pdf, self.vis_font_path) + self._thread.progressBarValue.connect(self.handleProgressBarSingal) + self._thread.endsignal.connect(self.handleEndsignalSignal) + self._thread.finished.connect(QObject.deleteLater) + self.time_start = 0 # save start time + + def setupUi(self): + self.setObjectName("MainWindow") + self.setWindowTitle(__APPNAME__ + " " + __VERSION__) + + layout = QGridLayout() + + self.openFileButton = QPushButton("打开文件") + self.openFileButton.setIcon(QIcon(QPixmap("./icons/folder-plus.png"))) + layout.addWidget(self.openFileButton, 0, 0, 1, 1) + self.openFileButton.clicked.connect(self.handleOpenFileSignal) + + # screenShotButton = QPushButton("截图识别") + # layout.addWidget(screenShotButton, 0, 1, 1, 1) + # screenShotButton.clicked.connect(self.screenShotSlot) + # screenShotButton.setEnabled(False) # temporarily disenble + + self.startCNButton = QPushButton("中文转换") + self.startCNButton.setIcon(QIcon(QPixmap("./icons/chinese.png"))) + layout.addWidget(self.startCNButton, 0, 1, 1, 1) + self.startCNButton.clicked.connect( + functools.partial(self.handleStartSignal, 'CN')) + + self.startENButton = QPushButton("英文转换") + self.startENButton.setIcon(QIcon(QPixmap("./icons/english.png"))) + layout.addWidget(self.startENButton, 0, 2, 1, 1) + self.startENButton.clicked.connect( + functools.partial(self.handleStartSignal, 'EN')) + + self.showResultButton = QPushButton("显示结果") + self.showResultButton.setIcon(QIcon(QPixmap("./icons/folder-open.png"))) + layout.addWidget(self.showResultButton, 0, 3, 1, 1) + self.showResultButton.clicked.connect(self.handleShowResultSignal) + + # ProgressBar + layout.addWidget(self.pb, 2, 0, 1, 4) + # time estimate label + self.timeEstLabel = QLabel( + ("Time Left: --")) + layout.addWidget(self.timeEstLabel, 3, 0, 1, 4) + + self.setLayout(layout) + + def downloadModels(self, URLs): + # using custom model + tar_file_name_list = [ + 'inference.pdiparams', + 'inference.pdiparams.info', + 'inference.pdmodel', + 'model.pdiparams', + 'model.pdiparams.info', + 'model.pdmodel' + ] + model_path = os.path.join(root, 'inference') + os.makedirs(model_path, exist_ok=True) + + # download and unzip models + for name in URLs.keys(): + url = URLs[name] + print("Try downloading file: {}".format(url)) + tarname = url.split('/')[-1] + tarpath = os.path.join(model_path, tarname) + if os.path.exists(tarpath): + print("File have already exist. skip") + else: + try: + download_with_progressbar(url, tarpath) + except Exception as e: + print("Error occurred when downloading file, error message:") + print(e) + + # unzip model tar + try: + with tarfile.open(tarpath, 'r') as tarObj: + storage_dir = os.path.join(model_path, name) + os.makedirs(storage_dir, exist_ok=True) + for member in tarObj.getmembers(): + filename = None + for tar_file_name in tar_file_name_list: + if tar_file_name in member.name: + filename = tar_file_name + if filename is None: + continue + file = tarObj.extractfile(member) + with open( + os.path.join(storage_dir, filename), + 'wb') as f: + f.write(file.read()) + except Exception as e: + print("Error occurred when unziping file, error message:") + print(e) + + def initPredictor(self, lang='EN'): + # init predictor args + args = parse_args() + args.table_max_len = 488 + args.ocr = True + args.recovery = True + args.save_pdf = self.save_pdf + args.table_char_dict_path = os.path.join(root, + "ppocr", "utils", "dict", "table_structure_dict.txt") + if lang == 'EN': + args.det_model_dir = os.path.join(root, # 此处从这里找到模型存放位置 + "inference", "en_PP-OCRv3_det_infer") + args.rec_model_dir = os.path.join(root, + "inference", "en_PP-OCRv3_rec_infer") + args.table_model_dir = os.path.join(root, + "inference", "en_ppstructure_mobile_v2.0_SLANet_infer") + args.output = os.path.join(root, "output") # 结果保存路径 + args.layout_model_dir = os.path.join(root, + "inference", "picodet_lcnet_x1_0_fgd_layout_infer") + lang_dict = DICT_EN + elif lang == 'CN': + args.det_model_dir = os.path.join(root, # 此处从这里找到模型存放位置 + "inference", "cn_PP-OCRv3_det_infer") + args.rec_model_dir = os.path.join(root, + "inference", "cn_PP-OCRv3_rec_infer") + args.table_model_dir = os.path.join(root, + "inference", "cn_ppstructure_mobile_v2.0_SLANet_infer") + args.output = os.path.join(root, "output") # 结果保存路径 + args.layout_model_dir = os.path.join(root, + "inference", "picodet_lcnet_x1_0_fgd_layout_cdla_infer") + lang_dict = DICT_CN + else: + raise ValueError("Unsupported language") + args.rec_char_dict_path = os.path.join(root, + "ppocr", "utils", + lang_dict['rec_char_dict_path']) + args.layout_dict_path = os.path.join(root, + "ppocr", "utils", "dict", "layout_dict", + lang_dict['layout_dict_path']) + # init predictor + return StructureSystem(args) + + def handleOpenFileSignal(self): + ''' + 可以多选图像文件 + ''' + selectedFiles = QFileDialog.getOpenFileNames(self, + "多文件选择", "/", "图片文件 (*.png *.jpeg *.jpg *.bmp *.pdf)")[0] + if len(selectedFiles) > 0: + self.imagePaths = selectedFiles + self.screenShot = None # discard screenshot temp image + self.pb.setRange(0, len(self.imagePaths)) + self.pb.setValue(0) + + def screenShotSlot(self): + ''' + 选定图像文件和截图的转换过程只能同时进行一个 + 截图只能同时转换一个 + ''' + self.screenShotWg.start() + if self.screenShotWg.captureImage: + self.screenShot = self.screenShotWg.captureImage + self.imagePaths.clear() # discard openfile temp list + self.pb.setRange(0, 1) + self.pb.setValue(0) + + def handleStartSignal(self, lang): + if self.screenShot: # for screenShot + img_name = 'screenshot_' + time.strftime("%Y%m%d%H%M%S", time.localtime()) + image = QImageToCvMat(self.screenShot) + self.predictAndSave(image, img_name, lang) + # update Progress Bar + self.pb.setValue(1) + QMessageBox.information(self, + u'Information', "文档提取完成") + elif len(self.imagePaths) > 0 : # for image file selection + # Must set image path list and language before start + self.output_dir = os.path.join( + os.path.dirname(self.imagePaths[0]), "output") # output_dir shold be same as imagepath + self._thread.setOutputDir(self.output_dir) + self._thread.setImagePath(self.imagePaths) + self._thread.setLang(lang) + # disenble buttons + self.openFileButton.setEnabled(False) + self.startCNButton.setEnabled(False) + self.startENButton.setEnabled(False) + # 启动工作进程 + self._thread.start() + self.time_start = time.time() # log start time + QMessageBox.information(self, + u'Information', "开始转换") + else: + QMessageBox.warning(self, + u'Information', "请选择要识别的文件或截图") + + def handleShowResultSignal(self): + if self.output_dir is None: + return + if os.path.exists(self.output_dir): + if platform.system() == 'Windows': + os.startfile(self.output_dir) + else: + os.system('open ' + os.path.normpath(self.output_dir)) + else: + QMessageBox.information(self, + u'Information', "输出文件不存在") + + def handleProgressBarSingal(self, i): + self.pb.setValue(i) + # calculate time left of recognition + lenbar = self.pb.maximum() + avg_time = (time.time() - self.time_start) / i # Use average time to prevent time fluctuations + time_left = str(datetime.timedelta(seconds=avg_time * (lenbar - i))).split(".")[0] # Remove microseconds + self.timeEstLabel.setText(f"Time Left: {time_left}") # show time left + + def handleEndsignalSignal(self): + # enble buttons + self.openFileButton.setEnabled(True) + self.startCNButton.setEnabled(True) + self.startENButton.setEnabled(True) + QMessageBox.information(self, u'Information', "转换结束") + + +def main(): + app = QApplication(sys.argv) + + window = APP_Image2Doc() # 创建对象 + window.show() # 全屏显示窗口 + + QApplication.processEvents() + sys.exit(app.exec()) + + +if __name__ == "__main__": + main() \ No newline at end of file From 322b41504a43ea7481c650cbb5862a4b55c4667c Mon Sep 17 00:00:00 2001 From: Evezerest <50011306+Evezerest@users.noreply.github.com> Date: Wed, 24 Aug 2022 16:43:29 +0800 Subject: [PATCH 12/14] Delete ScreenShotWidget.py --- ScreenShotWidget.py | 1108 ------------------------------------------- 1 file changed, 1108 deletions(-) delete mode 100644 ScreenShotWidget.py diff --git a/ScreenShotWidget.py b/ScreenShotWidget.py deleted file mode 100644 index 87d46198c0..0000000000 --- a/ScreenShotWidget.py +++ /dev/null @@ -1,1108 +0,0 @@ -# coding=utf-8 -# author: fardeas -# from: https://blog.csdn.net/u010501845/article/details/124931326 -import os -import sys -from datetime import datetime - -from qtpy import QtCore, QtGui -from qtpy.QtWidgets import * -from qtpy.QtCore import * -from qtpy.QtGui import * - - -class TextInputWidget(QTextEdit): - '''在截图区域内的文本输入框''' - - def __init__(self, god=None): - super().__init__(god) - self.god = god - # 设置背景透明 - # self.setStyleSheet("QTextEdit{background-color: transparent;}") - palette = self.palette() - palette.setBrush(QtGui.QPalette.ColorRole.Base, self.god.color_transparent) - self.setPalette(palette) - self.setTextColor(self.god.toolbar.curColor()) - self.setCurrentFont(self.god.toolbar.curFont()) - self._doc = self.document() # QTextDocument - self.textChanged.connect(self.adjustSizeByContent) - self.adjustSizeByContent() # 初始化调整高度为一行 - self.hide() - - def adjustSizeByContent(self, margin=30): - '''限制宽度不超出截图区域，根据文本内容调整高度，不会出现滚动条''' - self._doc.setTextWidth(self.viewport().width()) - margins = self.contentsMargins() - h = int(self._doc.size().height() + margins.top() + margins.bottom()) - self.setFixedHeight(h) - - def beginNewInput(self, pos, endPointF): - '''开始新的文本输入''' - self._maxRect = self.god.screenArea.normalizeRectF(pos, endPointF) - self.waitForInput() - - def waitForInput(self): - self.setGeometry(self._maxRect.toRect()) - # self.setGeometry(self._maxRect.adjusted(0, 0, -1, 0)) # 宽度-1 - self.setFocus() - self.show() - - def loadTextInputBy(self, action): - '''载入修改旧的文本 - action:(type, color, font, rectf, txt)''' - self.setTextColor(action[1]) - self.setCurrentFont(action[2]) - self._maxRect = action[3] - self.append(action[4]) - self.god.isDrawing = True - self.waitForInput() - - -class LineWidthAction(QAction): - - '''画笔粗细选择器''' - - def __init__(self, text, parent, lineWidth): - super().__init__(text, parent) - self._lineWidth = lineWidth - self.refresh(QtCore.Qt.GlobalColor.red) - self.triggered.connect(self.onTriggered) - self.setVisible(False) - - def refresh(self, color): - painter = self.parent().god.screenArea._painter - dotRadius = QPointF(self._lineWidth, self._lineWidth) - centerPoint = self.parent().iconPixmapCenter() - pixmap = self.parent().iconPixmapCopy() - painter.begin(pixmap) - painter.setPen(self.parent().god.pen_transparent) - painter.setBrush(color) - painter.drawEllipse(QRectF(centerPoint - dotRadius, centerPoint + dotRadius)) - painter.end() - self.setIcon(QIcon(pixmap)) - - def onTriggered(self): - self.parent()._curLineWidth = self._lineWidth - - -class FontAction(QAction): - - '''字体选择器''' - - def __init__(self, text, parent): - super().__init__(text, parent) - self.setIcon(QIcon(r"img/sys/font.png")) - self._curFont = self.parent().god.font_textInput - self.triggered.connect(self.onTriggered) - self.setVisible(False) - - def onTriggered(self): - font, ok = QFontDialog.getFont(self._curFont, self.parent(), caption='选择字体') - if ok: - self._curFont = font - self.parent().god.textInputWg.setCurrentFont(font) - - -class ColorAction(QAction): - - '''颜色选择器''' - - def __init__(self, text, parent): - super().__init__(text, parent) - self._curColor = QtCore.Qt.GlobalColor.red - self._pixmap = QPixmap(32, 32) - self.refresh(self._curColor) - self.triggered.connect(self.onTriggered) - - def refresh(self, color): - self._curColor = color - self._pixmap.fill(color) - self.setIcon(QIcon(self._pixmap)) - self.parent()._at_line_small.refresh(color) - self.parent()._at_line_normal.refresh(color) - self.parent()._at_line_big.refresh(color) - - def onTriggered(self): - col = QColorDialog.getColor(self._curColor, self.parent(), title='选择颜色') - if col.isValid(): - self.refresh(col) - self.parent().god.textInputWg.setTextColor(col) - - -class ScreenShotToolBar(QToolBar): - '''截图区域工具条''' - - def __init__(self, god): - super().__init__(god) - self.god = god - self.setToolButtonStyle(QtCore.Qt.ToolButtonStyle.ToolButtonTextUnderIcon) - self.setStyleSheet("QToolBar {border-radius: 5px;padding: 3px;background-color: #eeeeef;}") - self._style_normal = "QToolBar QToolButton{color: black;}" - self._style_selected = "QToolBar QToolButton{color: #ff7300;border: 1px solid #BEDAF2;background-color: #D6E4F1}" # 与鼠标悬停样式一样 - self._iconPixmap = QPixmap(32, 32) - self._iconPixmap.fill(self.god.color_transparent) - self._iconPixmapCenter = QPointF(self._iconPixmap.rect().center()) - self._curLineWidth = 3 - self._at_line_small = LineWidthAction('细', self, self._curLineWidth - 2) - self._at_line_normal = LineWidthAction('中', self, self._curLineWidth) - self._at_line_big = LineWidthAction('粗', self, self._curLineWidth + 2) - self._at_font = FontAction('字体', self) - self._at_color = ColorAction('颜色', self) - # self._at_rectangle = QAction(QIcon(r"img/sys/rectangle.png"), '矩形', self, triggered=self.beforeDrawRectangle) - # self._at_ellipse = QAction(QIcon(r"img/sys/ellipse.png"), '椭圆', self, triggered=self.beforeDrawEllipse) - # self._at_graffiti = QAction(QIcon(r"img/sys/graffiti.png"), '涂鸦', self, triggered=self.beforeDrawGraffiti) - # self._at_textInput = QAction(QIcon(r"img/sys/write.png"), '文字', self, triggered=self.beforeDrawText) - # self.addAction(self._at_line_small) - # self.addAction(self._at_line_normal) - # self.addAction(self._at_line_big) - # self.addAction(self._at_font) - # self.addAction(self._at_color) - # self.addSeparator() - # self.addAction(self._at_rectangle) - # self.addAction(self._at_ellipse) - # self.addAction(self._at_graffiti) - # self.addAction(self._at_textInput) - # self.addAction(QAction(QIcon(r"img/sys/undo.png"), '撤销', self, triggered=self.undo)) - # self.addSeparator() - self.addAction(QAction(QApplication.style().standardIcon(40), - '退出', self, triggered=self.god.rejectSlot)) - self.addAction(QAction(QApplication.style().standardIcon(45), - '接受', self, triggered=self.god.acceptSlot)) - # self.addAction(QAction(QIcon(r"img/chat/download.png"), '保存', self, triggered=lambda: self.beforeSave('local'))) - # self.addAction(QAction(QIcon(r"img/chat/sendImg.png"), '复制', self, triggered=lambda: self.beforeSave('clipboard'))) - # self.actionTriggered.connect(self.onActionTriggered) - - def curLineWidth(self): - return self._curLineWidth - - def curFont(self): - return self._at_font._curFont - - def curColor(self): - return self._at_color._curColor - # return QColor(self._at_color._curColor.toRgb()) # 颜色的副本 - - def iconPixmapCopy(self): - return self._iconPixmap.copy() - - def iconPixmapCenter(self): - return self._iconPixmapCenter - - # def onActionTriggered(self, action): - # '''突出显示已选中的画笔粗细、编辑模式''' - # for at in [self._at_line_small, self._at_line_normal, self._at_line_big]: - # if at._lineWidth == self._curLineWidth: - # self.widgetForAction(at).setStyleSheet(self._style_selected) - # else: - # self.widgetForAction(at).setStyleSheet(self._style_normal) - # if self.god.isDrawRectangle: - # self.widgetForAction(self._at_rectangle).setStyleSheet(self._style_selected) - # else: - # self.widgetForAction(self._at_rectangle).setStyleSheet(self._style_normal) - # if self.god.isDrawEllipse: - # self.widgetForAction(self._at_ellipse).setStyleSheet(self._style_selected) - # else: - # self.widgetForAction(self._at_ellipse).setStyleSheet(self._style_normal) - # if self.god.isDrawGraffiti: - # self.widgetForAction(self._at_graffiti).setStyleSheet(self._style_selected) - # else: - # self.widgetForAction(self._at_graffiti).setStyleSheet(self._style_normal) - # if self.god.isDrawText: - # self.widgetForAction(self._at_textInput).setStyleSheet(self._style_selected) - # else: - # self.widgetForAction(self._at_textInput).setStyleSheet(self._style_normal) - - def setLineWidthActionVisible(self, flag): - self._at_line_small.setVisible(flag) - self._at_line_normal.setVisible(flag) - self._at_line_big.setVisible(flag) - - def beforeDrawRectangle(self): - self.god.clearEditFlags() - self.god.isDrawRectangle = True - self.setLineWidthActionVisible(True) - self._at_font.setVisible(False) - - def beforeDrawEllipse(self): - self.god.clearEditFlags() - self.god.isDrawEllipse = True - self.setLineWidthActionVisible(True) - self._at_font.setVisible(False) - - def beforeDrawGraffiti(self): - self.god.clearEditFlags() - self.god.isDrawGraffiti = True - self.setLineWidthActionVisible(True) - self._at_font.setVisible(False) - - def beforeDrawText(self): - self.god.clearEditFlags() - self.god.isDrawText = True - self.setLineWidthActionVisible(False) - self._at_font.setVisible(True) - - def undo(self): - '''撤销上次编辑行为''' - if self.god.screenArea.undoEditAction(): - self.god.update() - - def beforeSave(self, target): - # 若正在编辑文本未保存，先完成编辑 - if self.god.isDrawing and self.god.isDrawText: - self.god.screenArea.saveTextInputAction() - if target == 'local': - self.god.save2Local() - elif target == 'clipboard': - self.god.save2Clipboard() - - def enterEvent(self, event): - self.god.setCursor(QtCore.Qt.CursorShape.ArrowCursor) # 工具条上显示标准箭头cursor - - def leaveEvent(self, event): - self.god.setCursor(QtCore.Qt.CursorShape.CrossCursor) # 十字无箭头 - - -class ScreenArea(QtCore.QObject): - '''屏幕区域（提供各种算法的核心类），划分为9个子区域： - TopLeft，Top，TopRight - Left，Center，Right - BottomLeft，Bottom，BottomRight - 其中Center根据start、end两个QPointF确定 - ''' - - def __init__(self, god): - super().__init__() - self.god = god - self._pt_start = QPointF() # 划定截图区域时鼠标左键按下的位置（topLeft） - self._pt_end = QPointF() # 划定截图区域时鼠标左键松开的位置（bottomRight） - self._rt_toolbar = QRectF() # 工具条的矩形 - self._actions = [] # 在截图区域上的所有编辑行为（矩形、椭圆、涂鸦、文本输入等） - self._pt_startEdit = QPointF() # 在截图区域上绘制矩形、椭圆时鼠标左键按下的位置（topLeft） - self._pt_endEdit = QPointF() # 在截图区域上绘制矩形、椭圆时鼠标左键松开的位置（bottomRight） - self._pointfs = [] # 涂鸦经过的所有点 - self._painter = QPainter() # 独立于ScreenShotWidget之外的画家类 - self._textOption = QtGui.QTextOption(QtCore.Qt.AlignmentFlag.AlignLeft | QtCore.Qt.AlignmentFlag.AlignTop) - self._textOption.setWrapMode(QtGui.QTextOption.WrapMode.WrapAnywhere) # 文本在矩形内自动换行 - # self._textOption.setWrapMode(QtGui.QTextOption.WrapMode.WrapAtWordBoundaryOrAnywhere) - self.captureScreen() - - def captureScreen(self): - '''抓取整个屏幕的截图''' - # screen = QtGui.QGuiApplication.primaryScreen() - self._screenPixmap = QApplication.primaryScreen().grabWindow(0) - self._pixelRatio = self._screenPixmap.devicePixelRatio() # 设备像素比 - self._rt_screen = self.screenLogicalRectF() - self.remakeNightArea() - - def normalizeRectF(self, topLeftPoint, bottomRightPoint): - '''根据起止点生成宽高非负数的QRectF，通常用于bottomRightPoint比topLeftPoint更左更上的情况 - 入参可以是QPoint或QPointF''' - rectf = QRectF(topLeftPoint, bottomRightPoint) - x = rectf.x() - y = rectf.y() - w = rectf.width() - h = rectf.height() - if w < 0: # bottomRightPoint在topLeftPoint左侧时，topLeftPoint往左移动 - x = x + w - w = -w - if h < 0: # bottomRightPoint在topLeftPoint上侧时，topLeftPoint往上移动 - y = y + h - h = -h - return QRectF(x, y, w, h) - - def physicalRectF(self, rectf): - '''计算划定的截图区域的（缩放倍率1.0的）原始矩形（会变大） - rectf：划定的截图区域的矩形。可为QRect或QRectF''' - return QRectF(rectf.x() * self._pixelRatio, rectf.y() * self._pixelRatio, - rectf.width() * self._pixelRatio, rectf.height() * self._pixelRatio) - - def logicalRectF(self, physicalRectF): - '''根据原始矩形计算缩放后的矩形（会变小） - physicalRectF：缩放倍率1.0的原始矩形。可为QRect或QRectF''' - return QRectF(physicalRectF.x() / self._pixelRatio, physicalRectF.y() / self._pixelRatio, - physicalRectF.width() / self._pixelRatio, physicalRectF.height() / self._pixelRatio) - - def physicalPixmap(self, rectf, editAction=False): - '''根据指定区域获取其原始大小的（缩放倍率1.0的）QPixmap - rectf：指定区域。可为QRect或QRectF - editAction:是否带上编辑结果''' - if editAction: - canvasPixmap = self.screenPhysicalPixmapCopy() - self._painter.begin(canvasPixmap) - self.paintEachEditAction(self._painter, textBorder=False) - self._painter.end() - return canvasPixmap.copy(self.physicalRectF(rectf).toRect()) - else: - return self._screenPixmap.copy(self.physicalRectF(rectf).toRect()) - - def screenPhysicalRectF(self): - return QRectF(self._screenPixmap.rect()) - - def screenLogicalRectF(self): - return QRectF(QPointF(0, 0), self.screenLogicalSizeF()) # 即当前屏幕显示的大小 - - def screenPhysicalSizeF(self): - return QSizeF(self._screenPixmap.size()) - - def screenLogicalSizeF(self): - return QSizeF(self._screenPixmap.width() / self._pixelRatio, self._screenPixmap.height() / self._pixelRatio) - - def screenPhysicalPixmapCopy(self): - return self._screenPixmap.copy() - - def screenLogicalPixmapCopy(self): - return self._screenPixmap.scaled(self.screenLogicalSizeF().toSize()) - - def centerPhysicalRectF(self): - return self.physicalRectF(self._rt_center) - - def centerLogicalRectF(self): - '''根据屏幕上的start、end两个QPointF确定''' - return self._rt_center - - def centerPhysicalPixmap(self, editAction=True): - '''截图区域的QPixmap - editAction:是否带上编辑结果''' - return self.physicalPixmap(self._rt_center + QMarginsF(-1, -1, 1, 1), editAction=editAction) - - def centerTopMid(self): - return self._pt_centerTopMid - - def centerBottomMid(self): - return self._pt_centerBottomMid - - def centerLeftMid(self): - return self._pt_centerLeftMid - - def centerRightMid(self): - return self._pt_centerRightMid - - def setStartPoint(self, pointf, remake=False): - self._pt_start = pointf - if remake: - self.remakeNightArea() - - def setEndPoint(self, pointf, remake=False): - self._pt_end = pointf - if remake: - self.remakeNightArea() - - def setCenterArea(self, start, end): - self._pt_start = start - self._pt_end = end - self.remakeNightArea() - - def remakeNightArea(self): - '''重新划分九宫格区域。根据中央截图区域计算出来的其他8个区域、截图区域四个边框中点坐标等都是logical的''' - self._rt_center = self.normalizeRectF(self._pt_start, self._pt_end) - # 中央区域上下左右边框的中点，用于调整大小 - self._pt_centerTopMid = (self._rt_center.topLeft() + self._rt_center.topRight()) / 2 - self._pt_centerBottomMid = (self._rt_center.bottomLeft() + self._rt_center.bottomRight()) / 2 - self._pt_centerLeftMid = (self._rt_center.topLeft() + self._rt_center.bottomLeft()) / 2 - self._pt_centerRightMid = (self._rt_center.topRight() + self._rt_center.bottomRight()) / 2 - # 以截图区域左上、上中、右上、左中、右中、左下、下中、右下为中心的正方形区域，用于调整大小 - self._square_topLeft = self.squareAreaByCenter(self._rt_center.topLeft()) - self._square_topRight = self.squareAreaByCenter(self._rt_center.topRight()) - self._square_bottomLeft = self.squareAreaByCenter(self._rt_center.bottomLeft()) - self._square_bottomRight = self.squareAreaByCenter(self._rt_center.bottomRight()) - self._square_topMid = self.squareAreaByCenter(self._pt_centerTopMid) - self._square_bottomMid = self.squareAreaByCenter(self._pt_centerBottomMid) - self._square_leftMid = self.squareAreaByCenter(self._pt_centerLeftMid) - self._square_rightMid = self.squareAreaByCenter(self._pt_centerRightMid) - # 除中央截图区域外的8个区域 - self._rt_topLeft = QRectF(self._rt_screen.topLeft(), self._rt_center.topLeft()) - self._rt_top = QRectF(QPointF(self._rt_center.topLeft().x(), 0), self._rt_center.topRight()) - self._rt_topRight = QRectF(QPointF(self._rt_center.topRight().x(), 0), QPointF(self._rt_screen.width(), self._rt_center.topRight().y())) - self._rt_left = QRectF(QPointF(0, self._rt_center.topLeft().y()), self._rt_center.bottomLeft()) - self._rt_right = QRectF(self._rt_center.topRight(), QPointF(self._rt_screen.width(), self._rt_center.bottomRight().y())) - self._rt_bottomLeft = QRectF(QPointF(0, self._rt_center.bottomLeft().y()), QPointF(self._rt_center.bottomLeft().x(), self._rt_screen.height())) - self._rt_bottom = QRectF(self._rt_center.bottomLeft(), QPointF(self._rt_center.bottomRight().x(), self._rt_screen.height())) - self._rt_bottomRight = QRectF(self._rt_center.bottomRight(), self._rt_screen.bottomRight()) - - def squareAreaByCenter(self, pointf): - '''以QPointF为中心的正方形QRectF''' - rectf = QRectF(0, 0, 15, 15) - rectf.moveCenter(pointf) - return rectf - - def aroundAreaIn8Direction(self): - '''中央区域周边的8个方向的区域（无交集）''' - return [self._rt_topLeft, self._rt_top, self._rt_topRight, - self._rt_left, self._rt_right, - self._rt_bottomLeft, self._rt_bottom, self._rt_bottomRight] - - def aroundAreaIn4Direction(self): - '''中央区域周边的4个方向的区域（有交集） - 上区域(左上、上、右上)：0, 0, maxX, topRight.y - 下区域(左下、下、右下)：0, bottomLeft.y, maxX, maxY-bottomLeft.y - 左区域(左上、左、左下)：0, 0, bottomLeft.x, maxY - 右区域(右上、右、右下)：topRight.x, 0, maxX - topRight.x, maxY''' - screenSizeF = self.screenLogicalSizeF() - pt_topRight = self._rt_center.topRight() - pt_bottomLeft = self._rt_center.bottomLeft() - return [QRectF(0, 0, screenSizeF.width(), pt_topRight.y()), - QRectF(0, pt_bottomLeft.y(), screenSizeF.width(), screenSizeF.height() - pt_bottomLeft.y()), - QRectF(0, 0, pt_bottomLeft.x(), screenSizeF.height()), - QRectF(pt_topRight.x(), 0, screenSizeF.width() - pt_topRight.x(), screenSizeF.height())] - - def aroundAreaWithoutIntersection(self): - '''中央区域周边的4个方向的区域（无交集） - 上区域(左上、上、右上)：0, 0, maxX, topRight.y - 下区域(左下、下、右下)：0, bottomLeft.y, maxX, maxY-bottomLeft.y - 左区域(左)：0, topRight.y, bottomLeft.x-1, center.height - 右区域(右)：topRight.x+1, topRight.y, maxX - topRight.x, center.height''' - screenSizeF = self.screenLogicalSizeF() - pt_topRight = self._rt_center.topRight() - pt_bottomLeft = self._rt_center.bottomLeft() - centerHeight = pt_bottomLeft.y() - pt_topRight.y() - return [QRectF(0, 0, screenSizeF.width(), pt_topRight.y()), - QRectF(0, pt_bottomLeft.y(), screenSizeF.width(), screenSizeF.height() - pt_bottomLeft.y()), - QRectF(0, pt_topRight.y(), pt_bottomLeft.x() - 1, centerHeight), - QRectF(pt_topRight.x() + 1, pt_topRight.y(), screenSizeF.width() - pt_topRight.x(), centerHeight)] - - def setBeginDragPoint(self, pointf): - '''计算开始拖拽位置距离截图区域左上角的向量''' - self._drag_vector = pointf - self._rt_center.topLeft() - - def getNewPosAfterDrag(self, pointf): - '''计算拖拽后截图区域左上角的新位置''' - return pointf - self._drag_vector - - def moveCenterAreaTo(self, pointf): - '''限制拖拽不能超出屏幕范围''' - self._rt_center.moveTo(self.getNewPosAfterDrag(pointf)) - startPointF = self._rt_center.topLeft() - if startPointF.x() < 0: - self._rt_center.moveTo(0, startPointF.y()) - startPointF = self._rt_center.topLeft() - if startPointF.y() < 0: - self._rt_center.moveTo(startPointF.x(), 0) - screenSizeF = self.screenLogicalSizeF() - endPointF = self._rt_center.bottomRight() - if endPointF.x() > screenSizeF.width(): - self._rt_center.moveBottomRight(QPointF(screenSizeF.width(), endPointF.y())) - endPointF = self._rt_center.bottomRight() - if endPointF.y() > screenSizeF.height(): - self._rt_center.moveBottomRight(QPointF(endPointF.x(), screenSizeF.height())) - self.setCenterArea(self._rt_center.topLeft(), self._rt_center.bottomRight()) - - def setBeginAdjustPoint(self, pointf): - '''判断开始调整截图区域大小时鼠标左键在哪个区（不可能是中央区域），用于判断调整大小的意图方向''' - self._mousePos = self.getMousePosBy(pointf) - - def getMousePosBy(self, pointf): - if self._square_topLeft.contains(pointf): - return 'TL' - elif self._square_topMid.contains(pointf): - return 'T' - elif self._square_topRight.contains(pointf): - return 'TR' - elif self._square_leftMid.contains(pointf): - return 'L' - elif self._rt_center.contains(pointf): - return 'CENTER' - elif self._square_rightMid.contains(pointf): - return 'R' - elif self._square_bottomLeft.contains(pointf): - return 'BL' - elif self._square_bottomMid.contains(pointf): - return 'B' - elif self._square_bottomRight.contains(pointf): - return 'BR' - else: - return 'ERROR' - - def adjustCenterAreaBy(self, pointf): - '''根据开始调整截图区域大小时鼠标左键在哪个区（不可能是中央区域），判断调整大小的意图方向，判定新的开始、结束位置''' - startPointF = self._rt_center.topLeft() - endPointF = self._rt_center.bottomRight() - if self._mousePos == 'TL': - startPointF = pointf - elif self._mousePos == 'T': - startPointF = QPointF(startPointF.x(), pointf.y()) - elif self._mousePos == 'TR': - startPointF = QPointF(startPointF.x(), pointf.y()) - endPointF = QPointF(pointf.x(), endPointF.y()) - elif self._mousePos == 'L': - startPointF = QPointF(pointf.x(), startPointF.y()) - elif self._mousePos == 'R': - endPointF = QPointF(pointf.x(), endPointF.y()) - elif self._mousePos == 'BL': - startPointF = QPointF(pointf.x(), startPointF.y()) - endPointF = QPointF(endPointF.x(), pointf.y()) - elif self._mousePos == 'B': - endPointF = QPointF(endPointF.x(), pointf.y()) - elif self._mousePos == 'BR': - endPointF = pointf - else: # 'ERROR' - return - newRectF = self.normalizeRectF(startPointF, endPointF) - self.setCenterArea(newRectF.topLeft(), newRectF.bottomRight()) - - def getMouseShapeBy(self, pointf): - '''根据鼠标位置返回对应的鼠标样式''' - if self._rt_center.contains(pointf): - if self.god.isDrawRectangle or self.god.isDrawEllipse: - return QtCore.Qt.CursorShape.ArrowCursor - elif self.god.isDrawGraffiti: - return QtCore.Qt.CursorShape.PointingHandCursor # 超链接上的手势 - elif self.god.isDrawText: - return QtCore.Qt.CursorShape.IBeamCursor # 工字 - else: - return QtCore.Qt.CursorShape.SizeAllCursor # 十字有箭头 - # return QtCore.Qt.CursorShape.OpenHandCursor # 打开的手，表示可拖拽 - elif self._square_topLeft.contains(pointf) or self._square_bottomRight.contains(pointf): - return QtCore.Qt.CursorShape.SizeFDiagCursor # ↖↘ - elif self._square_topMid.contains(pointf) or self._square_bottomMid.contains(pointf): - return QtCore.Qt.CursorShape.SizeVerCursor # ↑↓ - elif self._square_topRight.contains(pointf) or self._square_bottomLeft.contains(pointf): - return QtCore.Qt.CursorShape.SizeBDiagCursor # ↙↗ - elif self._square_leftMid.contains(pointf) or self._square_rightMid.contains(pointf): - return QtCore.Qt.CursorShape.SizeHorCursor # ←→ - else: - return QtCore.Qt.CursorShape.CrossCursor # 十字无箭头 - - def isMousePosInCenterRectF(self, pointf): - return self._rt_center.contains(pointf) - - def paintMagnifyingGlassPixmap(self, pos, glassSize): - '''绘制放大镜内的图像(含纵横十字线) - pos:鼠标光标位置 - glassSize:放大镜边框大小''' - pixmapRect = QRect(0, 0, 20, 20) # 以鼠标光标为中心的正方形区域，最好是偶数 - pixmapRect.moveCenter(pos) - glassPixmap = self.physicalPixmap(pixmapRect) - glassPixmap.setDevicePixelRatio(1.0) - glassPixmap = glassPixmap.scaled(glassSize, glassSize, QtCore.Qt.AspectRatioMode.KeepAspectRatio) - # 在放大后的QPixmap上画纵横十字线 - self._painter.begin(glassPixmap) - halfWidth = glassPixmap.width() / 2 - halfHeight = glassPixmap.height() / 2 - self._painter.setPen(self.god.pen_SolidLine_lightBlue) - self._painter.drawLine(QPointF(0, halfHeight), QPointF(glassPixmap.width(), halfHeight)) - self._painter.drawLine(QPointF(halfWidth, 0), QPointF(halfWidth, glassPixmap.height())) - self._painter.end() - return glassPixmap - - def paintEachEditAction(self, painter, textBorder=True): - '''绘制所有已保存的编辑行为。编辑行为超出截图区域也无所谓，保存图像时只截取截图区域内 - textBorder:是否绘制文本边框''' - for action in self.getEditActions(): - if action[0] == 'rectangle': # (type, color, lineWidth, startPoint, endPoint) - self.paintRectangle(painter, action[1], action[2], action[3], action[4]) - elif action[0] == 'ellipse': # (type, color, lineWidth, startPoint, endPoint) - self.paintEllipse(painter, action[1], action[2], action[3], action[4]) - elif action[0] == 'graffiti': # (type, color, lineWidth, points) - self.paintGraffiti(painter, action[1], action[2], action[3]) - elif action[0] == 'text': # (type, color, font, rectf, txt) - self.paintTextInput(painter, action[1], action[2], action[3], action[4], textBorder=textBorder) - - def paintRectangle(self, painter, color, lineWidth, startPoint=None, endPoint=None): - if not startPoint: - startPoint = self._pt_startEdit - if not endPoint: - endPoint = self._pt_endEdit - qrectf = self.normalizeRectF(startPoint, endPoint) - if qrectf.isValid(): - pen = QPen(color) - pen.setWidth(lineWidth) - painter.setPen(pen) - painter.setBrush(self.god.color_transparent) - painter.drawRect(qrectf) - - def paintEllipse(self, painter, color, lineWidth, startPoint=None, endPoint=None): - if not startPoint: - startPoint = self._pt_startEdit - if not endPoint: - endPoint = self._pt_endEdit - qrectf = self.normalizeRectF(startPoint, endPoint) - if qrectf.isValid(): - pen = QPen(color) - pen.setWidth(lineWidth) - painter.setPen(pen) - painter.setBrush(self.god.color_transparent) - painter.drawEllipse(qrectf) - - def paintGraffiti(self, painter, color, lineWidth, pointfs=None): - if not pointfs: - pointfs = self.getGraffitiPointFs() - pen = QPen(color) - pen.setWidth(lineWidth) - painter.setPen(pen) - total = len(pointfs) - if total == 0: - return - elif total == 1: - painter.drawPoint(pointfs[0]) - else: - previousPoint = pointfs[0] - for i in range(1, total): - nextPoint = pointfs[i] - painter.drawLine(previousPoint, nextPoint) - previousPoint = nextPoint - - def paintTextInput(self, painter, color, font, rectf, txt, textBorder=True): - painter.setPen(color) - painter.setFont(font) - painter.drawText(rectf, txt, self._textOption) - if textBorder: - painter.setPen(QtCore.Qt.PenStyle.DotLine) # 点线 - painter.setBrush(self.god.color_transparent) - painter.drawRect(rectf) - - def getEditActions(self): - return self._actions.copy() - - def takeTextInputActionAt(self, pointf): - '''根据鼠标位置查找已保存的文本输入结果，找到后取出''' - for i in range(len(self._actions)): - action = self._actions[i] - if action[0] == 'text' and action[3].contains(pointf): - return self._actions.pop(i) - return None - - def undoEditAction(self): - reply = False - if self._actions: - reply = self._actions.pop() - if not self._actions: # 所有编辑行为都被撤销后退出编辑模式 - self.god.exitEditMode() - else: - self.god.exitEditMode() - return reply - - def clearEditActions(self): - self._actions.clear() - - def setBeginEditPoint(self, pointf): - '''在截图区域上绘制矩形、椭圆时鼠标左键按下的位置（topLeft）''' - self._pt_startEdit = pointf - self.god.isDrawing = True - - def setEndEditPoint(self, pointf): - '''在截图区域上绘制矩形、椭圆时鼠标左键松开的位置（bottomRight）''' - self._pt_endEdit = pointf - - def saveRectangleAction(self): - rectf = self.normalizeRectF(self._pt_startEdit, self._pt_endEdit) - self._actions.append(('rectangle', self.god.toolbar.curColor(), self.god.toolbar.curLineWidth(), - rectf.topLeft(), rectf.bottomRight())) - self._pt_startEdit = QPointF() - self._pt_endEdit = QPointF() - self.god.isDrawing = False - - def saveEllipseleAction(self): - rectf = self.normalizeRectF(self._pt_startEdit, self._pt_endEdit) - self._actions.append(('ellipse', self.god.toolbar.curColor(), self.god.toolbar.curLineWidth(), - rectf.topLeft(), rectf.bottomRight())) - self._pt_startEdit = QPointF() - self._pt_endEdit = QPointF() - self.god.isDrawing = False - - def saveGraffitiPointF(self, pointf, first=False): - self._pointfs.append(pointf) - if first: - self.god.isDrawing = True - - def getGraffitiPointFs(self): - return self._pointfs.copy() - - def saveGraffitiAction(self): - if self._pointfs: - self._actions.append(('graffiti', self.god.toolbar.curColor(), self.god.toolbar.curLineWidth(), self._pointfs.copy())) - self._pointfs.clear() - self.god.isDrawing = False - - def setBeginInputTextPoint(self, pointf): - '''在截图区域上输入文字时鼠标左键按下的位置（topLeft）''' - self.god.isDrawing = True - self.god.textInputWg.beginNewInput(pointf, self._pt_end) - - def saveTextInputAction(self): - txt = self.god.textInputWg.toPlainText() - if txt: - rectf = self.god.textInputWg._maxRect # 取最大矩形的topLeft - rectf.setSize(QRectF(self.god.textInputWg.rect()).size()) # 取实际矩形的宽高 - self._actions.append(('text', self.god.toolbar.curColor(), self.god.toolbar.curFont(), - rectf, txt)) - self.god.textInputWg.clear() - self.god.textInputWg.hide() # 不管保存成功与否都取消编辑 - self.god.isDrawing = False - - def saveNightAreaImg(self): - '''将九宫格区域保存为本地图片，仅用于开发测试''' - screenPixmap = self.screenPhysicalPixmapCopy() - self._painter.begin(screenPixmap) - self._painter.setPen(self.pen_SolidLine_lightBlue) - self._painter.setFont(self.god.font_normal) - self._painter.drawRect(self._rt_center) - for area in self.aroundAreaIn8Direction(): - self._painter.drawRect(area) - for pointf in [self._rt_center.topLeft(), self._rt_center.topRight(), - self._rt_center.bottomLeft(), self._rt_center.bottomRight(), - self._pt_centerTopMid, self._pt_centerBottomMid, - self._pt_centerLeftMid, self._pt_centerRightMid]: - self._painter.drawText(pointf + QPointF(5, -5), '(%s, %s)' % (pointf.x(), pointf.y())) - self._painter.end() - screenPixmap.save('1.jpg', quality=100) - self.centerPhysicalPixmap().save('2.jpg', quality=100) - - -class ScreenShotWidget(QWidget): - - fileType_all = '所有文件 (*);;Excel文件 (*.xls *.xlsx);;图片文件 (*.jpg *.jpeg *.gif *.png *.bmp)' - fileType_img = '图片文件 (*.jpg *.jpeg *.gif *.png *.bmp)' - dir_lastAccess = os.getcwd() # 最后访问目录 - - def __init__(self): - super().__init__() - self.setMouseTracking(True) - self.setWindowFlags(QtCore.Qt.WindowType.FramelessWindowHint | QtCore.Qt.WindowType.WindowStaysOnTopHint) - self.initPainterTool() - self.initFunctionalFlag() - self.screenArea = ScreenArea(self) - self.toolbar = ScreenShotToolBar(self) - self.textInputWg = TextInputWidget(self) - - self.captureImage = None - # 设置 screenPixmap 为窗口背景 - # palette = QtGui.QPalette() - # palette.setBrush(QtGui.QPalette.ColorRole.Window, QtGui.QBrush(self.screenArea.screenPhysicalPixmapCopy())) - # self.setPalette(palette) - - def rejectSlot(self): - self.captureImage = None - self.close() - - def acceptSlot(self): - self.captureImage = self.screenArea.centerPhysicalPixmap().toImage() - self.close() - - def start(self): - self.screenArea.captureScreen() - self.setGeometry(self.screenArea.screenPhysicalRectF().toRect()) - self.clearScreenShotArea() - self.showFullScreen() - - def initPainterTool(self): - self.painter = QPainter() - self.color_transparent = QtCore.Qt.GlobalColor.transparent - self.color_black = QColor(0, 0, 0, 64) # 黑色背景 - self.color_lightBlue = QColor(30, 120, 255) # 浅蓝色。深蓝色QtCore.Qt.GlobalColor.blue - self.font_normal = QtGui.QFont('Times New Roman', 11, QtGui.QFont.Weight.Normal) - self.font_textInput = QtGui.QFont('微软雅黑', 16, QtGui.QFont.Weight.Normal) # 工具条文字工具默认字体 - self.pen_transparent = QPen(QtCore.Qt.PenStyle.NoPen) # 没有笔迹，画不出线条 - self.pen_white = QPen(QtCore.Qt.GlobalColor.white) - self.pen_SolidLine_lightBlue = QPen(self.color_lightBlue) # 实线，浅蓝色 - self.pen_SolidLine_lightBlue.setStyle(QtCore.Qt.PenStyle.DashLine) # 实线SolidLine，虚线DashLine，点线DotLine - self.pen_SolidLine_lightBlue.setWidthF(0) # 0表示线宽为1 - self.pen_DashLine_lightBlue = QPen(self.color_lightBlue) # 虚线，浅蓝色 - self.pen_DashLine_lightBlue.setStyle(QtCore.Qt.PenStyle.DashLine) - - def initFunctionalFlag(self): - self.hasScreenShot = False # 是否已通过拖动鼠标左键划定截图区域 - self.isCapturing = False # 正在拖动鼠标左键选定截图区域时 - self.isMoving = False # 在截图区域内拖动时 - self.isAdjusting = False # 在截图区域的边框按住鼠标左键调整大小时 - self.isDrawing = False # 是否已在截图区域内开始绘制 - self.isDrawRectangle = False # 正在截图区域内画矩形 - self.isDrawEllipse = False # 正在截图区域内画椭圆 - self.isDrawGraffiti = False # 正在截图区域内进行涂鸦 - self.isDrawText = False # 正在截图区域内画文字 - self.setCursor(QtCore.Qt.CursorShape.CrossCursor) # 设置鼠标样式 十字 - - def paintEvent(self, event): - centerRectF = self.screenArea.centerLogicalRectF() - screenSizeF = self.screenArea.screenLogicalSizeF() - canvasPixmap = self.screenArea.screenPhysicalPixmapCopy() - # canvasPixmap = QPixmap(screenSizeF.toSize()) - # canvasPixmap.fill(self.color_transparent) - # 在屏幕截图的副本上绘制已选定的截图区域 - self.painter.begin(canvasPixmap) - if self.hasScreenShot: - self.paintCenterArea(centerRectF) # 绘制中央截图区域 - self.paintMaskLayer(screenSizeF, fullScreen=False) # 绘制截图区域的周边区域遮罩层 - else: - self.paintMaskLayer(screenSizeF) - self.paintMagnifyingGlass(screenSizeF) # 在鼠标光标右下角显示放大镜 - self.paintToolbar(centerRectF, screenSizeF) # 在截图区域右下角显示工具条 - self.paintEditActions() # 在截图区域绘制编辑行为结果 - self.painter.end() - # 把画好的绘制结果显示到窗口上 - self.painter.begin(self) - self.painter.drawPixmap(0, 0, canvasPixmap) # 从坐标(0, 0)开始绘制 - self.painter.end() - - def paintCenterArea(self, centerRectF): - '''绘制已选定的截图区域''' - self.painter.setRenderHint(QPainter.RenderHint.Antialiasing, True) # 反走样 - # 1.绘制矩形线框 - self.painter.setPen(self.pen_DashLine_lightBlue) - self.painter.drawRect(centerRectF) - # 2.绘制矩形线框4个端点和4条边框的中间点 - if centerRectF.width() >= 100 and centerRectF.height() >= 100: - points = [ # 点坐标 - centerRectF.topLeft(), centerRectF.topRight(), centerRectF.bottomLeft(), centerRectF.bottomRight(), - self.screenArea.centerLeftMid(), self.screenArea.centerRightMid(), - self.screenArea.centerTopMid(), self.screenArea.centerBottomMid() - ] - blueDotRadius = QPointF(2, 2) # 椭圆蓝点 - self.painter.setBrush(self.color_lightBlue) - for point in points: - self.painter.drawEllipse(QRectF(point - blueDotRadius, point + blueDotRadius)) - # 3.在截图区域左上角显示截图区域宽高 - if centerRectF.topLeft().y() > 20: - labelPos = centerRectF.topLeft() + QPointF(5, -5) - else: # 拖拽截图区域到贴近屏幕上边缘时“宽x高”移动到截图区域左上角的下侧 - labelPos = centerRectF.topLeft() + QPointF(5, 15) - centerPhysicalRect = self.screenArea.centerPhysicalRectF().toRect() - self.painter.setPen(self.pen_white) - self.painter.setFont(self.font_normal) - self.painter.drawText(labelPos, '%s x %s' % (centerPhysicalRect.width(), centerPhysicalRect.height())) - # 4.在屏幕左上角预览截图结果 - # self.painter.drawPixmap(0, 0, self.screenArea.centerPhysicalPixmap()) # 从坐标(0, 0)开始绘制 - - def paintMaskLayer(self, screenSizeF, fullScreen=True): - if fullScreen: # 全屏遮罩层 - maskPixmap = QPixmap(screenSizeF.toSize()) - maskPixmap.fill(self.color_black) - self.painter.drawPixmap(0, 0, maskPixmap) - else: # 绘制截图区域的周边区域遮罩层，以凸显截图区域 - # 方法一：截图区域以外的8个方向区域 - # for area in self.screenArea.aroundAreaIn8Direction(): - # area = area.normalized() - # maskPixmap = QPixmap(area.size().toSize()) # 由于float转int的精度问题，可能会存在黑线条缝隙 - # maskPixmap.fill(self.color_black) - # self.painter.drawPixmap(area.topLeft(), maskPixmap) - # 方法二：截图区域以外的上下左右区域（有交集，交集部分颜色加深，有明显的纵横效果） - # for area in self.screenArea.aroundAreaIn4Direction(): - # maskPixmap = QPixmap(area.size().toSize()) - # maskPixmap.fill(self.color_black) - # self.painter.drawPixmap(area.topLeft(), maskPixmap) - # 方法三：截图区域以外的上下左右区域（无交集） - for area in self.screenArea.aroundAreaWithoutIntersection(): - maskPixmap = QPixmap(area.size().toSize()) - maskPixmap.fill(self.color_black) - self.painter.drawPixmap(area.topLeft(), maskPixmap) - - def paintMagnifyingGlass(self, screenSizeF, glassSize=150, offset=30, labelHeight=30): - '''未划定截图区域模式时、正在划定截取区域时、调整截取区域大小时在鼠标光标右下角显示放大镜 - glassSize:放大镜正方形边长 - offset:放大镜任意一个端点距离鼠标光标位置的最近距离 - labelHeight:pos和rgb两行文字的高度''' - if self.hasScreenShot and (not self.isCapturing) and (not self.isAdjusting): - return - pos = QtGui.QCursor.pos() - glassPixmap = self.screenArea.paintMagnifyingGlassPixmap(pos, glassSize) # 画好纵横十字线后的放大镜内QPixmap - # 限制放大镜显示不超出屏幕外 - glassRect = glassPixmap.rect() - if (pos.x() + glassSize + offset) < screenSizeF.width(): - if (pos.y() + offset + glassSize + labelHeight) < screenSizeF.height(): - glassRect.moveTo(pos + QPoint(offset, offset)) - else: - glassRect.moveBottomLeft(pos + QPoint(offset, -offset)) - else: - if (pos.y() + offset + glassSize + labelHeight) < screenSizeF.height(): - glassRect.moveTopRight(pos + QPoint(-offset, offset)) - else: - glassRect.moveBottomRight(pos + QPoint(-offset, -offset)) - self.painter.drawPixmap(glassRect.topLeft(), glassPixmap) - # 显示pos:(x, y)、rgb:(255,255,255) - qrgb = QtGui.QRgba64.fromArgb32(glassPixmap.toImage().pixel(glassPixmap.rect().center())) - labelRectF = QRectF(glassRect.bottomLeft().x(), glassRect.bottomLeft().y(), glassSize, labelHeight) - self.painter.setPen(self.pen_transparent) - self.painter.setBrush(self.color_black) # 黑底 - self.painter.drawRect(labelRectF) - self.painter.setPen(self.pen_white) - self.painter.setFont(self.font_normal) - self.painter.drawText(labelRectF, - QtCore.Qt.AlignmentFlag.AlignLeft | QtCore.Qt.AlignmentFlag.AlignVCenter, - 'pos:(%s, %s)\nrgb:(%s, %s, %s)' % (pos.x(), pos.y(), qrgb.red8(), qrgb.green8(), qrgb.blue8())) - - def paintToolbar(self, centerRectF, screenSizeF): - '''在截图区域右下角显示工具条''' - if self.hasScreenShot: - if self.isCapturing or self.isAdjusting: - self.toolbar.hide() # 正在划定截取区域时、调整截图区域大小时不显示工具条 - else: - self.toolbar.adjustSize() - toolbarRectF = QRectF(self.toolbar.rect()) - # 工具条位置优先顺序：右下角下侧，右上角上侧，右下角上侧 - if (screenSizeF.height() - centerRectF.bottomRight().y()) > toolbarRectF.height(): - toolbarRectF.moveTopRight(centerRectF.bottomRight() + QPointF(-5, 5)) - elif centerRectF.topRight().y() > toolbarRectF.height(): - toolbarRectF.moveBottomRight(centerRectF.topRight() + QPointF(-5, -5)) - else: - toolbarRectF.moveBottomRight(centerRectF.bottomRight() + QPointF(-5, -5)) - # 限制工具条的x坐标不为负数，不能移出屏幕外 - if toolbarRectF.x() < 0: - pos = toolbarRectF.topLeft() - pos.setX(centerRectF.x() + 5) - toolbarRectF.moveTo(pos) - self.toolbar.move(toolbarRectF.topLeft().toPoint()) - self.toolbar.show() - else: - self.toolbar.hide() - - def paintEditActions(self): - '''在截图区域绘制编辑行为结果。编辑行为超出截图区域也无所谓，保存图像时只截取截图区域内''' - # 1.绘制正在拖拽编辑中的矩形、椭圆、涂鸦 - if self.isDrawRectangle: - self.screenArea.paintRectangle(self.painter, self.toolbar.curColor(), self.toolbar.curLineWidth()) - elif self.isDrawEllipse: - self.screenArea.paintEllipse(self.painter, self.toolbar.curColor(), self.toolbar.curLineWidth()) - elif self.isDrawGraffiti: - self.screenArea.paintGraffiti(self.painter, self.toolbar.curColor(), self.toolbar.curLineWidth()) - # 2.绘制所有已保存的编辑行为 - self.screenArea.paintEachEditAction(self.painter) - - def clearEditFlags(self): - self.isDrawing = False - self.isDrawRectangle = False - self.isDrawEllipse = False - self.isDrawGraffiti = False - self.isDrawText = False - - def exitEditMode(self): - '''退出编辑模式''' - self.clearEditFlags() - # self.toolbar.onActionTriggered(None) # 清空工具条工具按钮选中状态 - self.textInputWg.hide() - - def clearScreenShotArea(self): - '''清空已划定的截取区域''' - self.screenArea.clearEditActions() # 清除已保存的编辑行为 - self.exitEditMode() - self.hasScreenShot = False - self.isCapturing = False - pos = QPointF() - self.screenArea.setCenterArea(pos, pos) - self.update() - self.setCursor(QtCore.Qt.CursorShape.CrossCursor) # 设置鼠标样式 十字 - - def mousePressEvent(self, event): - if event.button() == QtCore.Qt.MouseButton.LeftButton: - pos = event.pos() - if self.hasScreenShot: - if self.isDrawRectangle or self.isDrawEllipse: - self.screenArea.setBeginEditPoint(pos) - elif self.isDrawGraffiti: # 保存涂鸦经过的每一个点 - self.screenArea.saveGraffitiPointF(pos, first=True) - elif self.isDrawText: - if self.isDrawing: - if QRectF(self.textInputWg.rect()).contains(pos): - pass # 在输入框内调整光标位置，忽略 - else: # 鼠标点到输入框之外，完成编辑 - self.screenArea.saveTextInputAction() - else: # 未开始编辑时（暂不支持文本拖拽） - action = self.screenArea.takeTextInputActionAt(pos) - if action: # 鼠标点到输入框之内，修改旧的文本输入 - self.textInputWg.loadTextInputBy(action) - else: # 鼠标点到输入框之外，开始新的文本输入 - self.screenArea.setBeginInputTextPoint(pos) - elif self.screenArea.isMousePosInCenterRectF(pos): - self.isMoving = True # 进入拖拽移动模式 - self.screenArea.setBeginDragPoint(pos) - else: - self.isAdjusting = True # 进入调整大小模式 - self.screenArea.setBeginAdjustPoint(pos) - else: - self.screenArea.setCenterArea(pos, pos) - self.isCapturing = True # 进入划定截图区域模式 - if event.button() == QtCore.Qt.MouseButton.RightButton: - if self.hasScreenShot or self.isCapturing: # 清空已划定的的截图区域 - self.clearScreenShotArea() - else: - self.close() - - def mouseReleaseEvent(self, event): - if event.button() == QtCore.Qt.MouseButton.LeftButton: - if self.isDrawRectangle: - self.screenArea.saveRectangleAction() - elif self.isDrawEllipse: - self.screenArea.saveEllipseleAction() - elif self.isDrawGraffiti: - self.screenArea.saveGraffitiAction() - self.isCapturing = False - self.isMoving = False - self.isAdjusting = False - self.toolbar.show() - - def mouseMoveEvent(self, event): - pos = event.pos() - if self.isDrawing: - if self.isDrawRectangle or self.isDrawEllipse: - self.screenArea.setEndEditPoint(pos) - elif self.isDrawGraffiti: - self.screenArea.saveGraffitiPointF(pos) - elif self.isCapturing: - self.hasScreenShot = True - self.screenArea.setEndPoint(pos, remake=True) - elif self.isMoving: - self.screenArea.moveCenterAreaTo(pos) - elif self.isAdjusting: - self.screenArea.adjustCenterAreaBy(pos) - self.update() - if self.hasScreenShot: - self.setCursor(self.screenArea.getMouseShapeBy(pos)) - else: - self.setCursor(QtCore.Qt.CursorShape.CrossCursor) # 设置鼠标样式 十字 - - def mouseDoubleClickEvent(self, event): - if event.button() == QtCore.Qt.MouseButton.LeftButton: - if self.screenArea.isMousePosInCenterRectF(event.pos()): - self.save2Clipboard() - self.close() - - def keyPressEvent(self, QKeyEvent): - if QKeyEvent.key() == QtCore.Qt.Key.Key_Escape: - self.close() - if QKeyEvent.key() in (QtCore.Qt.Key.Key_Return, QtCore.Qt.Key.Key_Enter): # 大键盘、小键盘回车 - self.save2Clipboard() - self.close() - - def save2Clipboard(self): - '''将截图区域复制到剪贴板''' - if self.hasScreenShot: - mimData = QtCore.QMimeData() - mimData.setImageData(self.screenArea.centerPhysicalPixmap().toImage()) - QApplication.clipboard().setMimeData(mimData) - # self.screenArea.saveNightAreaImg() - self.close() - - def save2Local(self): - fileType = self.fileType_img - filePath, fileFormat = self.sys_selectSaveFilePath(self, fileType=fileType) - if filePath: - self.screenArea.centerPhysicalPixmap().save(filePath, quality=100) - self.close() - - def sys_getCurTime(self, fmt='%Y-%m-%d %H:%M:%S'): - '''获取字符串格式的当前时间''' - # return QtCore.QDateTime.currentDateTime().toString('yyyy-MM-dd hh:mm:ss') - return datetime.now().strftime(fmt) - - def sys_selectSaveFilePath(self, widget, title='选择文件保存路径', saveFileDir=None, - saveFileName='', defaultFileFmt='%Y%m%d%H%M%S', fileType=None): - '''选择文件保存路径 - title:选择窗口标题 - saveFileDir:指定保存目录 - saveFileName:默认保存文件名 - defaultFileFmt:不指定saveFileName时，自动以此格式的时间字符串命名文件 - fileType:可以选择的文件类型 - return:(所选的文件保存路径, 文件的类型) - ''' - options = QFileDialog.Option.ReadOnly - if saveFileName == '': - saveFileName = self.sys_getCurTime(defaultFileFmt) - if not saveFileDir: - saveFileDir = self.dir_lastAccess - saveFilePath = os.path.join(saveFileDir, saveFileName) - if not fileType: - fileType = self.fileType_all - filePath, fileFormat = QFileDialog.getSaveFileName(widget, title, saveFilePath, fileType, options=options) - if filePath: - self.dir_lastAccess = os.path.dirname(filePath) - return (filePath, fileFormat) - - From 3c79159d74b18d7fe21e4373ff3b3516bb7ef619 Mon Sep 17 00:00:00 2001 From: Evezerest <50011306+Evezerest@users.noreply.github.com> Date: Wed, 24 Aug 2022 16:44:14 +0800 Subject: [PATCH 13/14] Update pdf2word.py --- ppstructure/pdf2word/pdf2word.py | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) diff --git a/ppstructure/pdf2word/pdf2word.py b/ppstructure/pdf2word/pdf2word.py index add8a6f405..b05886f62a 100644 --- a/ppstructure/pdf2word/pdf2word.py +++ b/ppstructure/pdf2word/pdf2word.py @@ -21,7 +21,7 @@ from ppstructure.predict_system import StructureSystem, save_structure_res from ppstructure.utility import parse_args, draw_structure_result from ppocr.utils.network import download_with_progressbar from ppstructure.recovery.recovery_to_doc import sorted_layout_boxes, convert_info_docx -from ScreenShotWidget import ScreenShotWidget +# from ScreenShotWidget import ScreenShotWidget __APPNAME__ = "pdf2word" __VERSION__ = "0.1.1" @@ -181,7 +181,7 @@ class APP_Image2Doc(QWidget): # settings self.imagePaths = [] - self.screenShotWg = ScreenShotWidget() +# self.screenShotWg = ScreenShotWidget() self.screenShot = None self.save_pdf = False self.output_dir = None @@ -358,17 +358,17 @@ class APP_Image2Doc(QWidget): self.pb.setRange(0, len(self.imagePaths)) self.pb.setValue(0) - def screenShotSlot(self): - ''' - 选定图像文件和截图的转换过程只能同时进行一个 - 截图只能同时转换一个 - ''' - self.screenShotWg.start() - if self.screenShotWg.captureImage: - self.screenShot = self.screenShotWg.captureImage - self.imagePaths.clear() # discard openfile temp list - self.pb.setRange(0, 1) - self.pb.setValue(0) +# def screenShotSlot(self): +# ''' +# 选定图像文件和截图的转换过程只能同时进行一个 +# 截图只能同时转换一个 +# ''' +# self.screenShotWg.start() +# if self.screenShotWg.captureImage: +# self.screenShot = self.screenShotWg.captureImage +# self.imagePaths.clear() # discard openfile temp list +# self.pb.setRange(0, 1) +# self.pb.setValue(0) def handleStartSignal(self, lang): if self.screenShot: # for screenShot @@ -438,4 +438,4 @@ def main(): if __name__ == "__main__": - main() \ No newline at end of file + main() From d106954a02e358d77bff557dff582f2423440797 Mon Sep 17 00:00:00 2001 From: Evezerest <50011306+Evezerest@users.noreply.github.com> Date: Wed, 24 Aug 2022 16:46:25 +0800 Subject: [PATCH 14/14] Update pdf2word.md --- ppstructure/pdf2word/pdf2word.md | 19 ++----------------- 1 file changed, 2 insertions(+), 17 deletions(-) diff --git a/ppstructure/pdf2word/pdf2word.md b/ppstructure/pdf2word/pdf2word.md index 8d69d60748..564df4063e 100644 --- a/ppstructure/pdf2word/pdf2word.md +++ b/ppstructure/pdf2word/pdf2word.md @@ -1,11 +1,6 @@ # PDF2WORD -PDF2WORD是PaddleOCR社区开发者@whj 基于PP-Structure智能文档分析模型实现的PDF转换Word应用程序，提供可直接安装的exe，方便windows用户运行 - -
- -
- +PDF2WORD是PaddleOCR社区开发者[whjdark](https://github.com/whjdark) 基于PP-Structure智能文档分析模型实现的PDF转换Word应用程序，提供可直接安装的exe，方便windows用户运行 ## 1.使用 @@ -23,17 +18,7 @@ PDF2WORD是PaddleOCR社区开发者@whj 基于PP-Structure智能文档分析模 python pdf2word.py ``` -## 2.自行打包 - -PDF2WORD应用程序通过[QPT](https://github.com/QPT-Family/QPT)工具打包实现，若您修改了界面代码需要重新打包，请在 `PaddleOCR` 文件夹下运行下方指令 - -``` -cd ./ -mv ./ppstructure/pdf2word .. -r -python GenEXE.py -``` - -## 3.软件下载 +## 2.软件下载 如需获取已打包程序，可以扫描下方二维码，关注公众号填写问卷后，加入PaddleOCR官方交流群免费获取20G OCR学习大礼包，内含OCR场景应用集合（包含数码管、液晶屏、车牌、高精度SVTR模型等7个垂类模型）、《动手学OCR》电子书、课程回放视频、前沿论文等重磅资料