calibre/recipes/caijing.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

91 lines
3.6 KiB
Plaintext

import re
from calibre.web.feeds.recipes import BasicNewsRecipe
__license__ = 'GPL v3'
class Caijing(BasicNewsRecipe):
'''based on the recipe wrote by Eric Chen at 2011'''
__author__ = '2014, Chen Wei <weichen302@gmx.com>'
title = 'Caijing Magazine'
description = '''
Founded in 1998, the fortnightly CAIJING Magazine has firmly established
itself as a news authority and leading voice for business and financial
issues in China.
CAIJING Magazine closely tracks the most important aspects of China's
economic reforms, developments and policy changes, as well as major events
in the capital markets. It also offers a broad international perspective
through first-hand reporting on international political and economic
issues.
CAIJING Magazine is China's most widely read business and finance magazine,
with a circulation of 225,000 per issue. It boasts top-level readers from
government, business and academic circles.'''
language = 'zh'
encoding = 'UTF-8'
publisher = 'Caijing Magazine'
publication_type = 'magazine'
category = 'news, Business, China'
timefmt = ' [%a, %d %b, %Y]'
needs_subscription = True
remove_tags = [dict(attrs={'class': ['head_nav', 'mcont_logo', 'header',
'bottom', 'footer', 'magazine_ipad', 'cjartShare', 'ar_about',
'main_rt', 'mcont_nav', 'new']}),
dict(attrs={'id': ['articlePl']}),
dict(name=['script', 'noscript', 'style'])]
no_stylesheets = True
remove_javascript = True
current_issue_url = ""
current_issue_cover = ""
def get_browser(self):
br = BasicNewsRecipe.get_browser(self)
if self.username is not None and self.password is not None:
br.open('http://service.caijing.com.cn/usermanage/login')
br.select_form(name='mainLoginForm')
br['username'] = self.username
br['password'] = self.password
br.submit()
return br
def parse_index(self):
soup_start = self.index_to_soup('http://magazine.caijing.com.cn/')
jumpurl = soup_start.find('script').contents[0].split()
for line in jumpurl:
if 'http' in line.lower():
issuesurl = line.split('"')[1]
break
soup_issues = self.index_to_soup(issuesurl)
# find the latest issue
div = soup_issues.find('div', attrs={'class': 'fmcon'})
current_issue_url = div.find('a', href=True)['href']
soup = self.index_to_soup(current_issue_url)
coverimg = soup.find('div', {'class': 'zzfm_img'})
self.current_issue_cover = coverimg.find('img')['src']
feeds = []
for section in soup.findAll('div',
attrs={'class': re.compile(r'(fmwz_ml|zzlm_nr)2?$')}):
section_title = self.tag_to_string(section.find('div',
attrs={'class': re.compile(r'(lmnav_bt|zzlm_bt)1?$')}))
self.log('Found section:', section_title)
articles = []
for post in section.findAll('div',
attrs={'class': re.compile(r'(fmwz_bt|zzlm_nr_bt)')}):
title = self.tag_to_string(post)
url = post.find('a')['href']
articles.append({'title': title, 'url': url, 'date': None})
if articles:
feeds.append((section_title, articles))
return feeds
def get_cover_url(self):
return self.current_issue_cover