xiaoxue_admin
/
RSSHub
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fix: 中国政府网吹风会和新闻页面格式调整 (#4406)

This commit is contained in:
EsuRt 2020-04-13 19:34:12 +08:00 committed by GitHub
parent 5c42be33b7
commit 8a5dbbcc1f
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 48 additions and 32 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

68
lib/routes/gov/news/index.js
View File

@ -55,37 +55,53 @@ module.exports = async (ctx) => {
let fullTextGet = '';
if (item.html().search(/dysMiddleResultConItemTitle/g) !== -1) {
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();
} else {
return fullTextData('#UCAP-CONTENT').html();
}
});
if (contentUrl.search(/content/g) === -1) {
description = item.find('a').text(); // 忽略获取吹风会的全文
} else {
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) {
fullTextData('.shuzi').remove(); // 移除videobg的图片
fullTextData('#myFlash').remove(); // 移除flash
return fullTextData('.pages_content').html();
} else {
fullTextData('.shuzi').remove(); // 移除videobg的图片
fullTextData('#myFlash').remove(); // 移除flash
return fullTextData('#UCAP-CONTENT').html();
}
});
}
} else {
href = item.find('a').attr('href');
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 (contentUrl.search(/zhengceku/g) !== -1) {
fullText = fullTextData('.pages_content').html();
} else {
if ($1.search(/UCAP-CONTENT/g) === -1) {
fullText = fullTextData('body').html();
if (contentUrl.search(/content/g) === -1) {
description = item.find('a').text(); // 忽略获取吹风会的全文
} else {
description = await ctx.cache.tryGet(contentUrl, async () => {
fullTextGet = await got.get(contentUrl);
fullTextData = cheerio.load(fullTextGet.data);
const $1 = fullTextData.html();
if (contentUrl.search(/zhengceku/g) !== -1) {
// 政策文件库
fullText = fullTextData('.pages_content').html();
} else {
fullTextData('.shuzi').remove();
fullText = fullTextData('#UCAP-CONTENT').html();
if ($1.search(/UCAP-CONTENT/g) === -1) {
fullTextData('.shuzi').remove(); // 移除videobg的图片
fullTextData('#myFlash').remove(); // 移除flash
fullText = fullTextData('body').html();
} else {
fullTextData('.shuzi').remove(); // 移除videobg的图片
fullTextData('#myFlash').remove(); // 移除flash
fullText = fullTextData('#UCAP-CONTENT').html();
}
}
}
const regImg = /(img src=")(.*)(".*)/g;
const regUrl = /(http.*\/)(content.*)/;
const urlSplit = contentUrl.replace(regUrl, '$1');
return fullText.replace(regImg, '$1' + urlSplit + '$2' + '$3');
});
const regImg = /(img src=")(.*)(".*)/g;
const regUrl = /(http.*\/)(content.*)/;
const urlSplit = contentUrl.replace(regUrl, '$1');
return fullText.replace(regImg, '$1' + urlSplit + '$2' + '$3'); // 处理图片链接
});
}
}
return {
title: item.find('a').text(),

12
lib/routes/gov/statecouncil/briefing.js
View File

@ -16,14 +16,14 @@ module.exports = async (ctx) => {
.map(async (index, item) => {
item = $(item);
const contenlUrl = item.find('a').attr('href');
const description = await ctx.cache.tryGet(contenlUrl, async () => {
const fullText = await got.get(contenlUrl);
const fullTextData = cheerio.load(fullText.data);
return fullTextData('.online_list').html();
});
// const description = await ctx.cache.tryGet(contenlUrl, async () => {
// const fullText = await got.get(contenlUrl);
// const fullTextData = cheerio.load(fullText.data);
// return fullTextData('.online_list').html();
// });
return {
title: item.find('a').text(),
description: description,
description: item.find('a').text(),
link: contenlUrl,
};
})