Compare commits

...

3 Commits

4 changed files with 207 additions and 2 deletions

125
qinghai/2020-02-08_275.html Normal file
View File

@ -0,0 +1,125 @@
<!DOCTYPE html><html><head>
<link rel="icon" data-savepage-href="http://www.nhc.gov.cn/favicon.ico" href="">
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
<meta charset="utf-8">
<meta http-equiv="X-UA-Compatible" content="IE=edge">
<meta name="viewport" content="width=device-width, initial-scale=1">
<meta name="viewport" content="width=device-width, initial-scale=1, maximum-scale=1.0, user-scalable=no">
<meta name="SiteName" content="宣传司">
<meta name="SiteDomain" content="">
<meta name="SiteIDCode" content="">
<meta name="ColumnName" content="通知公告">
<meta name="ColumnDescription" content="">
<meta name="ColumnKeywords" content="">
<meta name="ColumnType" content="">
<meta name="ArticleTitle" content="国家卫生健康委关于新型冠状病毒肺炎暂命名事宜的通知">
<meta name="PubDate" content="2020-04-22 09:34:47">
<meta name="Keywords" content="">
<meta name="Description" content="">
<meta name="others" content="页面生成时间 2020-04-22 09:34:47">
<meta name="template,templategroup,version" content="adb7c6acf2db4cc19c609ea5121b3d79,default,1.1">
<title>国家卫生健康委关于新型冠状病毒肺炎暂命名事宜的通知</title>
<link href="/xcs/xhtml/css/publics.css" type="text/css" rel="stylesheet">
<link rel="stylesheet" type="text/css" href="/xcs/xhtml/css/xxgzbd.css">
<link href="/xcs/xhtml/css/list.css" type="text/css" rel="stylesheet">
<!--[if lt IE 9]><script r='m'>document.createElement("section")</script><![endif]--><script data-savepage-type="" type="text/plain" data-savepage-src="/xcs/xhtml/js/jquery-1.8.3.min.js"></script>
<script data-savepage-type="text/javascript" type="text/plain"></script>
<script data-savepage-type="" type="text/plain"></script>
<script data-savepage-type="" type="text/plain" data-savepage-src="http://bdimg.share.baidu.com/static/api/js/share.js?v=89860593.js?cdnversion=458201"></script><style type="text/css">@media print {
.TridactylStatusIndicator {
display: none !important;
}
}</style><link rel="stylesheet" href="http://bdimg.share.baidu.com/static/api/css/share_style0_16.css?v=8105b07e.css">
<style id="savepage-cssvariables">
:root {
--savepage-url-5: url(data:image/png;base64,);
--savepage-url-6: url(data:image/png;base64,);
--savepage-url-10: url(data:image/png;base64,);
}
</style>
<script id="savepage-shadowloader" type="application/javascript">
"use strict";
window.addEventListener("DOMContentLoaded",
function(event) {
savepage_ShadowLoader(5);
},false);
function savepage_ShadowLoader(c){createShadowDOMs(0,document.documentElement);function createShadowDOMs(a,b){var i;if(b.localName=="iframe"||b.localName=="frame"){if(a<c){try{if(b.contentDocument.documentElement!=null){createShadowDOMs(a+1,b.contentDocument.documentElement)}}catch(e){}}}else{if(b.children.length>=1&&b.children[0].localName=="template"&&b.children[0].hasAttribute("data-savepage-shadowroot")){b.attachShadow({mode:"open"}).appendChild(b.children[0].content);b.removeChild(b.children[0]);for(i=0;i<b.shadowRoot.children.length;i++)if(b.shadowRoot.children[i]!=null)createShadowDOMs(a,b.shadowRoot.children[i])}for(i=0;i<b.children.length;i++)if(b.children[i]!=null)createShadowDOMs(a,b.children[i])}}}
</script>
<meta name="savepage-url" content="http://www.nhc.gov.cn/xcs/zhengcwj/202002/18c1bb43965a4492907957875de02ae7.shtml">
<meta name="savepage-title" content="国家卫生健康委关于新型冠状病毒肺炎暂命名事宜的通知">
<meta name="savepage-pubdate" content="Unknown">
<meta name="savepage-from" content="http://www.nhc.gov.cn/xcs/zhengcwj/202002/18c1bb43965a4492907957875de02ae7.shtml">
<meta name="savepage-date" content="Sat Apr 09 2022 19:11:51 GMT+0100 (British Summer Time)">
<meta name="savepage-state" content="Basic Items; Retain cross-origin frames; Merge CSS images; Remove unsaved URLs; Load lazy images in existing content; Max frame depth = 5; Max resource size = 50MB; Max resource time = 10s;">
<meta name="savepage-version" content="27.3">
<meta name="savepage-comments" content="">
</head><iframe class="cleanslate hidden" data-savepage-src="moz-extension://4c36391b-a5be-4bdf-a527-2faf208ce26c/static/commandline.html" src="" id="cmdline_iframe" loading="lazy" style="height: 0px !important;" data-savepage-key="0-0"></iframe>
<body>
<script data-savepage-type="" type="text/plain" language="JavaScript"></script>
<script data-savepage-type="text/javascript" type="text/plain" charset="utf-8" id="kpyfx_js_id_10006654" data-savepage-src="//fxsjcj.kaipuyun.cn/count/10006654/10006654.js"></script>
<div class="banner"><img data-savepage-currentsrc="http://www.nhc.gov.cn/xcs/xhtml/images/gzbdbanner.png" data-savepage-src="/xcs/xhtml/images/gzbdbanner.png" src="" class="bannerimg"></div>
<div class="banner banner_ydd"><img data-savepage-currentsrc="http://www.nhc.gov.cn/xcs/xhtml/images/gzbdbanner_ydd.png" data-savepage-src="/xcs/xhtml/images/gzbdbanner_ydd.png" src="" class="bannerimg"></div>
<div class="w1024 mb50">
<div class="index_title">
<h3 class="index_title_h3 fl">通知公告</h3>
<div class="fr loc">您现在所在位置:
<a data-savepage-href="/xcs/new_index.shtml" href="http://www.nhc.gov.cn/xcs/new_index.shtml" target="_parent">首页</a> &gt; <a data-savepage-href="/xcs/xxgzbd/gzbd_index.shtml" href="http://www.nhc.gov.cn/xcs/xxgzbd/gzbd_index.shtml" target="_parent">新型冠状病毒肺炎疫情防控</a> &gt; <a data-savepage-href="/xcs/zhengcwj/list_gzbd.shtml" href="http://www.nhc.gov.cn/xcs/zhengcwj/list_gzbd.shtml" target="_parent"><span>通知公告</span></a>
</div>
<div class="clear"></div>
</div>
<div class="list">
<div class="tit">国家卫生健康委关于新型冠状病毒肺炎暂命名事宜的通知</div>
<div class="source">
<div class="fr"><span><a href="#" onclick="changeSize('16px');return false;"><img data-savepage-currentsrc="http://www.nhc.gov.cn/xcs/xhtml/images/sm.jpg" data-savepage-src="/xcs/xhtml/images/sm.jpg" src=""></a></span><span><a href="#" onclick="changeSize('20px');return false;"><img data-savepage-currentsrc="http://www.nhc.gov.cn/xcs/xhtml/images/big.jpg" data-savepage-src="/xcs/xhtml/images/big.jpg" src=""></a></span><span><a href="javascript:window.print()"><img data-savepage-currentsrc="http://www.nhc.gov.cn/xcs/xhtml/images/dys.jpg" data-savepage-src="/xcs/xhtml/images/dys.jpg" src=""></a></span></div>
<span>发布时间:
2020-02-08
</span>
<span class="mr">来源:
医政医管局
</span>
<div class="clear"></div>
</div>
<div class="con" id="xw_box">
<p style="text-align: right; line-height: 1.5; font-family: 仿宋, 仿宋_GB2312; font-size: 20px;">国卫医函202042号<br>
</p>
<p style="line-height: 1.5; font-family: 仿宋, 仿宋_GB2312; font-size: 20px;"></p>
<p style="text-align: justify; line-height: 1.5; font-family: 仿宋, 仿宋_GB2312; font-size: 20px;">各省、自治区、直辖市人民政府,新疆生产建设兵团,国务院应对新型冠状病毒肺炎疫情联防联控机制成员:<br>
  现决定将“新型冠状病毒感染的肺炎”暂命名为“新型冠状病毒肺炎”简称“新冠肺炎”英文名称为“Novel Coronavirus Pneumonia”简称“NCP”。<br>
</p>
<p style="text-align: justify; line-height: 1.5; font-family: 仿宋, 仿宋_GB2312; font-size: 20px;"></p>
<p style="text-align: justify; line-height: 1.5; font-family: 仿宋, 仿宋_GB2312; font-size: 20px;"></p>
<p style="text-align: right; line-height: 1.5; font-family: 仿宋, 仿宋_GB2312; font-size: 20px;">国家卫生健康委</p>
<p style="text-align: right; line-height: 1.5; font-family: 仿宋, 仿宋_GB2312; font-size: 20px;">2020年2月7日</p>
<p style="text-align: justify; line-height: 1.5; font-family: 仿宋, 仿宋_GB2312; font-size: 20px;"></p>
<p style="text-align: justify; line-height: 1.5; font-family: 仿宋, 仿宋_GB2312; font-size: 20px;">  (信息公开形式:主动公开)</p>
<div class="fx fr" style="font-size: 20px;">
<div class="bdsharebuttonbox fr bdshare-button-style0-16" data-bd-bind="1649527526839" style="font-size: 20px;">
<a href="#" class="bds_more" data-cmd="more"></a><a href="#" class="bds_qzone" data-cmd="qzone" title="分享到QQ空间"></a><a href="#" class="bds_tsina" data-cmd="tsina" title="分享到新浪微博"></a><a href="#" class="bds_tqq" data-cmd="tqq" title="分享到腾讯微博"></a><a href="#" class="bds_renren" data-cmd="renren" title="分享到人人网"></a><a href="#" class="bds_weixin" data-cmd="weixin" title="分享到微信"></a>
</div>
<script data-savepage-type="" type="text/plain"></script>
分享到  
</div>
<div class="clear" style="font-size: 20px;"></div>
</div>
</div>
</div>
<div class="ttbg">
<div class="w1200 bottom">
<div class="dzjg fl"><a href="http://bszs.conac.cn/sitename?method=show&id=095F1802D253655FE053022819AC11D8" target="_blank"><img data-savepage-currentsrc="http://www.nhc.gov.cn/xcs/xhtml/images/logo_foot.png" data-savepage-src="/xcs/xhtml/images/logo_foot.png" src="" width="46" height=""></a></div>
<p>地址北京市西城区西直门外南路1号邮编100044电话010-68792114ICP备案编号京ICP备18052910号 京公网安备 11010202000005号</p>
<p>中华人民共和国国家卫生健康委员会版权所有技术支持国家卫生健康委员会统计信息中心网站标识码bm24000006</p>
</div>
</div>
<span class="cleanslate TridactylStatusIndicator TridactylModenormal">normal</span></body></html>

53
qinghai/README.md Normal file
View File

@ -0,0 +1,53 @@
## Qinghai scraping
A few links don't exist anymore. They have the indexes 210, 453, 681,
703, 791, 871, 913, 914, 915 in `links.csv`.
There are a few small files again, mostly pdf links:
```console
.rw-r--r-- 101 tlater 9 Apr 19:26 ./2016-09-28_923.txt
.rw-r--r-- 133 tlater 9 Apr 19:26 ./2016-09-28_924.txt
.rw-r--r-- 116 tlater 9 Apr 19:26 ./2016-09-28_925.txt
.rw-r--r-- 147 tlater 9 Apr 19:26 ./2016-09-28_926.txt
.rw-r--r-- 111 tlater 9 Apr 19:23 ./2017-03-16_838.txt
.rw-r--r-- 36 tlater 9 Apr 19:20 ./2017-07-07_745.txt
.rw-r--r-- 82 tlater 9 Apr 19:17 ./2017-08-14_723.txt
.rw-r--r-- 211 tlater 9 Apr 19:17 ./2017-09-12_704.txt
.rw-r--r-- 97 tlater 9 Apr 19:14 ./2017-11-15_587.txt
.rw-r--r-- 156 tlater 9 Apr 19:13 ./2017-11-20_580.txt
.rw-r--r-- 283 tlater 9 Apr 19:13 ./2017-11-23_575.txt
.rw-r--r-- 39 tlater 9 Apr 19:13 ./2017-12-29_566.txt
.rw-r--r-- 39 tlater 9 Apr 19:13 ./2018-01-12_561.txt
.rw-r--r-- 165 tlater 9 Apr 19:12 ./2018-05-30_505.txt
.rw-r--r-- 145 tlater 9 Apr 19:12 ./2018-05-30_507.txt
.rw-r--r-- 391 tlater 9 Apr 19:11 ./2018-07-25_475.txt
.rw-r--r-- 158 tlater 9 Apr 19:11 ./2018-09-13_467.txt
.rw-r--r-- 204 tlater 9 Apr 19:04 ./2020-03-09_254.txt
.rw-r--r-- 124 tlater 9 Apr 19:04 ./2020-03-18_248.txt
.rw-r--r-- 228 tlater 9 Apr 19:04 ./2020-03-20_245.txt
.rw-r--r-- 186 tlater 9 Apr 19:03 ./2020-04-01_221.txt
.rw-r--r-- 67 tlater 9 Apr 19:02 ./2020-04-21_208.txt
.rw-r--r-- 174 tlater 9 Apr 19:01 ./2020-04-30_194.txt
.rw-r--r-- 147 tlater 9 Apr 19:01 ./2020-05-08_186.txt
.rw-r--r-- 189 tlater 9 Apr 19:01 ./2020-05-12_182.txt
.rw-r--r-- 82 tlater 9 Apr 19:01 ./2020-05-15_180.txt
.rw-r--r-- 119 tlater 9 Apr 19:00 ./2020-06-04_139.txt
.rw-r--r-- 201 tlater 9 Apr 19:00 ./2020-07-01_114.txt
.rw-r--r-- 113 tlater 9 Apr 18:59 ./2020-07-20_90.txt
.rw-r--r-- 115 tlater 9 Apr 18:59 ./2020-07-21_86.txt
.rw-r--r-- 99 tlater 9 Apr 18:58 ./2020-08-27_36.txt
.rw-r--r-- 99 tlater 9 Apr 18:58 ./2020-08-27_37.txt
.rw-r--r-- 130 tlater 9 Apr 18:58 ./2020-08-27_38.txt
.rw-r--r-- 130 tlater 9 Apr 18:58 ./2020-08-27_39.txt
.rw-r--r-- 190 tlater 9 Apr 18:58 ./2020-08-27_40.txt
.rw-r--r-- 190 tlater 9 Apr 18:58 ./2020-08-27_41.txt
.rw-r--r-- 184 tlater 9 Apr 18:58 ./2020-08-27_42.txt
.rw-r--r-- 184 tlater 9 Apr 18:58 ./2020-08-27_43.txt
.rw-r--r-- 127 tlater 9 Apr 18:58 ./2020-08-27_44.txt
.rw-r--r-- 127 tlater 9 Apr 18:58 ./2020-08-27_45.txt
.rw-r--r-- 94 tlater 9 Apr 18:58 ./2020-08-27_46.txt
.rw-r--r-- 94 tlater 9 Apr 18:58 ./2020-08-27_47.txt
.rw-r--r-- 88 tlater 9 Apr 18:58 ./2020-09-12_20.txt
.rw-r--r-- 200 tlater 9 Apr 18:57 ./2020-09-21_11.txt
```

24
qinghai/scrape-iframe.py Normal file
View File

@ -0,0 +1,24 @@
"""Script to scrape contents from a specific article.
This is for
http://www.nhc.gov.cn/xcs/zhengcwj/202002/18c1bb43965a4492907957875de02ae7.shtml.
For whatever reason, this article is implemented as an iframe, so
requires downloading with a full-featured browser. It's just one
though, so let's parse it.
"""
from bs4 import BeautifulSoup
def main():
"""Scrape html site."""
with open("2020-02-08_275.html", "r") as f:
soup = BeautifulSoup(f.read(), "html.parser")
text = soup.find(class_="w1024").get_text().strip()
with open("articles-qinghai/2020-02-08_275.txt", "w+") as f:
f.write(text)
if __name__ == "__main__":
main()

View File

@ -35,8 +35,11 @@ def main():
writer.writerow(i, link[0], link[1])
for i, link in enumerate(links):
# Broken link
if i == 210:
# Broken links
#
# 275 was available as an iframe, and is parsed separately in
# scrape-iframe.py
if i in (210, 275, 453, 681, 703, 791, 871, 913, 914, 915):
continue
print(f"Downloading {link[0]} ({i}/{len(links)})")