opensource/RSSHub
3
0
Fork 0
mirror of https://github.com/DIYgod/RSSHub.git synced 2026-09-24 23:12:34 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: 调整中国政府网新闻排版，更改苏州政府网政策文件网址 (#3710)

Browse Source
This commit is contained in:
EsuRt
2020-01-14 11:43:36 +08:00
committed by DIYgod
parent 60b9e07098
commit 93167c346a
2 changed files with 28 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files
lib/routes/gov/news/index.js
+11 -10
View File
@@ -49,14 +49,14 @@ module.exports = async (ctx) => {
item = $(item);
let fullText = '';
let href = '';
let contenlUrl = '';
let contentUrl = '';
let description = '';
let fullTextData = '';
let fullTextGet = '';
if (item.html().search(/dysMiddleResultConItemTitle/g) !== -1) {
contenlUrl = item.find('a').attr('href');
description = await ctx.cache.tryGet(contenlUrl, async () => {
fullTextGet = await got.get(contenlUrl);
contentUrl = item.find('a').attr('href');
description = await ctx.cache.tryGet(contentUrl, async () => {
fullTextGet = await got.get(contentUrl);
fullTextData = cheerio.load(fullTextGet.data);
if (fullTextData.html().search(/pages_content/g) !== -1) {
return fullTextData('.pages_content').html();
@@ -66,30 +66,31 @@ module.exports = async (ctx) => {
});
} else {
href = item.find('a').attr('href');
contenlUrl = href.startsWith('/') ? `http://www.gov.cn${href}` : href;
description = await ctx.cache.tryGet(contenlUrl, async () => {
fullTextGet = await got.get(contenlUrl);
contentUrl = href.startsWith('/') ? `http://www.gov.cn${href}` : href;
description = await ctx.cache.tryGet(contentUrl, async () => {
fullTextGet = await got.get(contentUrl);
fullTextData = cheerio.load(fullTextGet.data);
const $1 = fullTextData.html();
if (contenlUrl.search(/zhengceku/g) !== -1) {
if (contentUrl.search(/zhengceku/g) !== -1) {
fullText = fullTextData('.pages_content').html();
} else {
if ($1.search(/UCAP-CONTENT/g) === -1) {
fullText = fullTextData('body').html();
} else {
fullTextData('.shuzi').remove();
fullText = fullTextData('#UCAP-CONTENT').html();
}
}
const regImg = /(img src=")(.*)(".*)/g;
const regUrl = /(http.*\/)(content.*)/;
const urlSplit = contenlUrl.replace(regUrl, '$1');
const urlSplit = contentUrl.replace(regUrl, '$1');
return fullText.replace(regImg, '$1' + urlSplit + '$2' + '$3');
});
}
return {
title: item.find('a').text(),
description: description,
link: contenlUrl,
link: contentUrl,
};
})
.get()
lib/routes/gov/suzhou/doc.js
+17 -20
View File
@@ -2,41 +2,38 @@ const got = require('@/utils/got');
const cheerio = require('cheerio');
module.exports = async (ctx) => {
const link = 'http://www.zfxxgk.suzhou.gov.cn/sxqzf/szsrmzf/index_1073.html';
const link = 'http://www.suzhou.gov.cn/szxxgk/front/xxgk_right.jsp?sitecode=szsrmzf';
const response = await got.get(link);
const data = response.data;
const str = cheerio.load(data);
const strSelect = str('script:not([src])')[0].children[0].data;
const list = strSelect.match(/(url:".)(\/.*html)"/g);
const $ = cheerio.load(data);
const list = $('.tr_main_value_odd');
ctx.state.data = {
title: '苏州市政府 - 政策公开文件',
link: link,
item: await Promise.all(
list &&
list.slice(1, 10).map(async (index, item) => {
list
.slice(1, 12)
.map(async (index, item) => {
item = $(item);
// 获取全文
const contenlhref = list[item].replace(/(url:".)(\/.*html)"/, '$2');
const contenlUrl = 'http://www.zfxxgk.suzhou.gov.cn/sxqzf/szsrmzf' + contenlhref;
const arr = await ctx.cache.tryGet(contenlUrl, async () => {
const fullText = await got.get(contenlUrl);
const contentUrl = 'http://www.suzhou.gov.cn' + item.find('a').attr('href');
const arr = await ctx.cache.tryGet(contentUrl, async () => {
const fullText = await got.get(contentUrl);
const fullTextData = cheerio.load(fullText.data);
fullTextData('h1').remove();
const textSelect = fullTextData('body').html();
// 处理图片地址
const regImg = /(src=")(\.\/)(.*\.jpg)/g;
const regpdf = /(href=")(\.\/)(.*\.pdf)/g;
const regUrl = /(http.*\/)(.*)(\.html)/;
const urlSplit = contenlUrl.replace(regUrl, '$1');
return new Array(fullTextData('article h2').text(), textSelect.replace(regImg, '$1' + urlSplit + '$3').replace(regpdf, '$1' + urlSplit + '$3'));
const description = fullTextData('.content').html();
const title = fullTextData('.title.bold')
.text()
.replace(/\s*/g, '');
return new Array(title, description);
});
return {
title: arr[0],
description: arr[1],
link: contenlUrl,
link: contentUrl,
};
})
.get()
),
};
};