calibre/recipes/globaltimes.recipe
Kovid Goyal 567040ee1e Perform PEP8 compliance checks on the entire codebase
Some bits of PEP 8 are turned off via setup.cfg
2016-07-29 21:25:17 +05:30

50 lines
2.1 KiB
Plaintext

from calibre.web.feeds.news import BasicNewsRecipe
import re
class globaltimes(BasicNewsRecipe):
title = u'Global Times'
__author__ = 'malfi'
language = 'zh'
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'}))
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;}
'''
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"
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)
articles.append(myarticle)
self.log("Adding URL %s\n" % url)
if articles:
feeds.append((catnames[cat], articles))
return feeds