opensource/we-mp-rss
3
0
Fork 0
mirror of https://github.com/rachelos/we-mp-rss.git synced 2026-09-24 16:02:42 +08:00
Code Issues Packages Projects Releases Wiki Activity

v1.4.1

Browse Source
This commit is contained in:
t@123654
2025-06-11 19:44:08 +08:00
parent 9ed40afef7
commit 60f3cd5799
8 changed files with 81 additions and 70 deletions
Download Patch File Download Diff File Expand all files Collapse all files
core/models/article.py
+1 -1
View File
@@ -6,7 +6,7 @@ class Article(Base):
title = Column(String(500))
pic_url = Column(String(500))
url=Column(String(500))
content = Column(MEDIUMTEXT)
content = Column(Text)
description=Column(String(800))
status = Column(Integer,default=1)
publish_time = Column(Integer)
core/wx/wx1.py
+31 -28
View File
@@ -6,39 +6,42 @@ import yaml
import re
from bs4 import BeautifulSoup
from .base import WxGather
from core.log import logger
# 继承 BaseGather 类
class MpsApi(WxGather):
# 重写 content_extract 方法
def content_extract(self, url):
session=self.session
r = session.get(url, headers=self.headers)
if r.status_code == 200:
text = r.text
if text is None:
return
soup = BeautifulSoup(text, 'html.parser')
# 找到内容
js_content_div = soup.find('div', {'id': 'js_content'})
# 移除style属性中的visibility: hidden;
if js_content_div is None:
return
js_content_div.attrs.pop('style', None)
# 找到所有的img标签
img_tags = js_content_div.find_all('img')
# 遍历每个img标签并修改属性，设置宽度为1080p
for img_tag in img_tags:
if 'data-src' in img_tag.attrs:
img_tag['src'] = img_tag['data-src']
del img_tag['data-src']
if 'style' in img_tag.attrs:
style = img_tag['style']
# 使用正则表达式替换width属性
style = re.sub(r'width\s*:\s*\d+\s*px', 'width: 1080px', style)
img_tag['style'] = style
return js_content_div.prettify()
return None
try:
session=self.session
r = session.get(url, headers=self.headers)
if r.status_code == 200:
text = r.text
if text is None:
return
soup = BeautifulSoup(text, 'html.parser')
# 找到内容
js_content_div = soup.find('div', {'id': 'js_content'})
# 移除style属性中的visibility: hidden;
if js_content_div is None:
return
js_content_div.attrs.pop('style', None)
# 找到所有的img标签
img_tags = js_content_div.find_all('img')
# 遍历每个img标签并修改属性，设置宽度为1080p
for img_tag in img_tags:
if 'data-src' in img_tag.attrs:
img_tag['src'] = img_tag['data-src']
del img_tag['data-src']
if 'style' in img_tag.attrs:
style = img_tag['style']
# 使用正则表达式替换width属性
style = re.sub(r'width\s*:\s*\d+\s*px', 'width: 1080px', style)
img_tag['style'] = style
return js_content_div.prettify()
except Exception as e:
logger.error(e)
return ""
# 重写 get_Articles 方法
def get_Articles(self, faker_id:str=None,Mps_id:str=None,Mps_title="",CallBack=None,begin=0,MaxPage:int=1,interval=1,Gather_Content=False,Item_Over_CallBack=None,Over_CallBack=None):
super().Start(mp_id=Mps_id)
core/wx/wx2.py
+31 -28
View File
@@ -6,39 +6,42 @@ import yaml
import re
from bs4 import BeautifulSoup
from .base import WxGather
from core.log import logger
# 继承 BaseGather 类
class MpsWeb(WxGather):
# 重写 content_extract 方法
def content_extract(self, url):
session=self.session
r = session.get(url, headers=self.headers)
if r.status_code == 200:
text = r.text
if text is None:
return
soup = BeautifulSoup(text, 'html.parser')
# 找到内容
js_content_div = soup.find('div', {'id': 'js_content'})
# 移除style属性中的visibility: hidden;
if js_content_div is None:
return
js_content_div.attrs.pop('style', None)
# 找到所有的img标签
img_tags = js_content_div.find_all('img')
# 遍历每个img标签并修改属性，设置宽度为1080p
for img_tag in img_tags:
if 'data-src' in img_tag.attrs:
img_tag['src'] = img_tag['data-src']
del img_tag['data-src']
if 'style' in img_tag.attrs:
style = img_tag['style']
# 使用正则表达式替换width属性
style = re.sub(r'width\s*:\s*\d+\s*px', 'width: 1080px', style)
img_tag['style'] = style
return js_content_div.prettify()
return None
try:
session=self.session
r = session.get(url, headers=self.headers)
if r.status_code == 200:
text = r.text
if text is None:
return
soup = BeautifulSoup(text, 'html.parser')
# 找到内容
js_content_div = soup.find('div', {'id': 'js_content'})
# 移除style属性中的visibility: hidden;
if js_content_div is None:
return
js_content_div.attrs.pop('style', None)
# 找到所有的img标签
img_tags = js_content_div.find_all('img')
# 遍历每个img标签并修改属性，设置宽度为1080p
for img_tag in img_tags:
if 'data-src' in img_tag.attrs:
img_tag['src'] = img_tag['data-src']
del img_tag['data-src']
if 'style' in img_tag.attrs:
style = img_tag['style']
# 使用正则表达式替换width属性
style = re.sub(r'width\s*:\s*\d+\s*px', 'width: 1080px', style)
img_tag['style'] = style
return js_content_div.prettify()
except Exception as e:
logger.error(e)
return ""
# 重写 get_Articles 方法
def get_Articles(self, faker_id:str=None,Mps_id:str=None,Mps_title="",CallBack=None,begin:int=0,MaxPage:int=1,interval=1,Gather_Content=False,Item_Over_CallBack=None,Over_CallBack=None):
super().Start(mp_id=Mps_id)
db.db
BIN
View File
Binary file not shown.
init_sys.py
+1
View File
@@ -26,6 +26,7 @@ def sync_models():
# 同步模型到表结构
from core.data_sync import ModelSync
DB.create_tables()
time.sleep(3)
sync=ModelSync(eng=DB.get_engine())
sync.sync_all()
print_info("模型同步完成")
jobs/fetch_no_article.py
+5 -7
View File
@@ -2,6 +2,7 @@ from core.models.article import Article
from core.db import DB
from core.wx.base import WxGather
from time import sleep
from core.print import print_success,print_error
import random
def fetch_articles_without_content():
"""
@@ -24,24 +25,21 @@ def fetch_articles_without_content():
else:
url = f"https://mp.weixin.qq.com/s/{article.id}"
print(f"正在处理文章: {article.id}, URL: {url}")
print(f"正在处理文章: {article.title}, URL: {url}")
# 获取内容
content = ga.content_extract(url)
sleep(random.randint(1,5))
sleep(random.randint(3,10))
if content:
# 更新内容
article.content = content
session.commit()
print(f"成功更新文章 {article.title} 的内容")
print_success(f"成功更新文章 {article.title} 的内容")
else:
print(f"获取文章 {article.title} 内容失败")
print_error(f"获取文章 {article.title} 内容失败")
except Exception as e:
print(f"处理过程中发生错误: {e}")
session.rollback()
finally:
session.close()
from core.task import TaskScheduler
scheduler=TaskScheduler()
from core.config import cfg
jobs/webhook.py
+2 -1
View File
@@ -110,7 +110,8 @@ def web_hook(hook:MessageWebHook):
# 处理articles参数，兼容Article对象和字典类型
processed_articles = []
if len(hook.articles)<=0:
raise ValueError("没有更新到文章")
# raise ValueError("没有更新到文章")
logger.warning("没有更新到文章")
return
for article in hook.articles:
if isinstance(article, dict):
publish.bat
+10 -5
View File
@@ -33,9 +33,14 @@ if %WEB_FLAG%==1 (
REM 读取Python配置文件中的版本号
for /f "tokens=1 delims==" %%v in ('python -c "from core.ver import VERSION; print(VERSION)"') do set VERSION=%%v
set tag="v%VERSION%"
if "%VERSION%"=="" (
echo 错误：无法从core.ver.py读取版本号
exit /b 1
)
set tag=v%VERSION%
echo 当前版本: %VERSION% TAG: %tag%
REM 设置comment
if %COMMENT_FLAG%==1 (
set comment=%USER_COMMENT%
@@ -45,13 +50,13 @@ if %COMMENT_FLAG%==1 (
if exist %version_file% (
for /f "usebackq delims=" %%a in (%version_file%) do set comment=%%a
) else (
echo 警告：未找到对应版本号的文件 %version_file%
echo "警告：未找到对应版本号的文件%version_file%"
)
)
echo %comment%
echo "%comment%"
git add .
git tag "v%VERSION%"
git tag -a "v%VERSION%" -m "%VERSION% %comment%"
git commit -m "%VERSION% %comment%"
REM 执行git操作
@@ -60,4 +65,4 @@ if %PUSH_FLAG%==1 (
git push origin %tag%
git push -u gitee main
git push gitee %tag%
)
)