Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Global Times

Browse Source 
Fixes #1825937 [can't fetch news of globaltimes](https://bugs.launchpad.net/calibre/+bug/1825937)
This commit is contained in:
Kovid Goyal 2019-04-24 11:21:47 +05:30
parent 4b8d853999
commit 8f829e6de6
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 46 additions and 25 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

71
recipes/globaltimes.recipe
View File

@ -2,46 +2,67 @@ from calibre.web.feeds.news import BasicNewsRecipe
import re
class globaltimes(BasicNewsRecipe):
def classes(classes):
q = frozenset(classes.split(' '))
return dict(
attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)}
)
class GlobalTimes(BasicNewsRecipe):
title = u'Global Times'
__author__ = 'malfi'
language = 'zh'
__author__ = 'Jose Ortiz' # lui1 at mobileread.com
language = 'en_CN'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
cover_url = 'http://enhimg2.huanqiu.com/images/logo.png'
language = 'en'
keep_only_tags = []
keep_only_tags.append(dict(name='div', attrs={'id': 'content'}))
remove_tags = []
remove_tags.append(dict(name='div', attrs={'class': 'location'}))
remove_tags.append(dict(name='div', attrs={'class': 'contentpage'}))
remove_tags.append(dict(name='li', attrs={'id': 'pl'}))
keep_only_tags = [classes('article-title article-source row-content')]
extra_css = '''
h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
.article-title {
font-family:Arial,Helvetica,sans-serif;
font-weight:bold;font-size:large;
}
.article-source, .row-content {
font-family:Arial,Helvetica,sans-serif;
font-size:small;
}
'''
def parse_index(self):
catnames = {}
catnames["http://china.globaltimes.cn/chinanews/"] = "China Politics"
catnames["http://china.globaltimes.cn/diplomacy/"] = "China Diplomacy"
catnames["http://military.globaltimes.cn/china/"] = "China Military"
catnames["http://business.globaltimes.cn/china-economy/"] = "China Economy"
catnames["http://world.globaltimes.cn/asia-pacific/"] = "Asia Pacific"
catnames["http://www.globaltimes.cn/china/politics/"] = "China Politics"
catnames["http://www.globaltimes.cn/china/diplomacy/"] = "China Diplomacy"
catnames["http://www.globaltimes.cn/china/military/"] = "China Military"
catnames["http://www.globaltimes.cn/business/economy/"] = "China Economy"
catnames["http://www.globaltimes.cn/world/asia-pacific/"] = "Asia Pacific"
feeds = []
for cat in catnames.keys():
articles = []
soup = self.index_to_soup(cat)
for a in soup.findAll('a', attrs={'href': re.compile(cat + "201[0-9]-[0-1][0-9]/[0-9][0-9][0-9][0-9][0-9][0-9].html")}):
url = a['href'].strip()
myarticle = ({'title': self.tag_to_string(
a), 'url': url, 'description': '', 'date': ''})
self.log("found %s" % url)
for a in soup.findAll(
'a',
attrs={
'href':
re.compile(
r'https?://www.globaltimes.cn/content/[0-9]{4,10}[.]shtml'
)
}
):
url = a['href'].strip(
) # Typical url http://www.globaltimes.cn/content/5555555.shtml
title = self.tag_to_string(a).strip()
if not title:
continue
myarticle = ({
'title': title,
'url': url,
'description': '',
'date': ''
})
self.log("found '%s'" % title)
articles.append(myarticle)
self.log("Adding URL %s\n" % url)
if articles: