Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-08-07 09:01:38 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Caijing

Browse Source
This commit is contained in:
Kovid Goyal 2014-01-01 13:18:22 +05:30
parent c497dc1097
commit 225ebd4231
1 changed files with 49 additions and 37 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

86
recipes/caijing.recipe
View File

@ -1,38 +1,47 @@
import re
from calibre.web.feeds.recipes import BasicNewsRecipe
__license__ = 'GPL v3'
class Caijing(BasicNewsRecipe):
title = 'Caijing Magazine'
__author__ = 'Eric Chen'
'''based on the recipe wrote by Eric Chen at 2011'''
description = '''Bi-weekly Finance and Economics Review. 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. '''
__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'
category = 'news, China'
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':['topad', 'nav', 'searchbox', 'connav',
'mbx', 'bianji', 'bianji bj', 'lnewlist', 'rdtj', 'loadComment',
'conr', 'bottom', 'bottomcopyr', 'emaildy', 'rcom', 'allcontent']}),
dict(name=['script', 'noscript', 'style'])]
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:
@ -44,31 +53,34 @@ class Caijing(BasicNewsRecipe):
return br
def parse_index(self):
articles = []
soup0 = self.index_to_soup('http://magazine.caijing.com.cn/2011/cjindex2011/')
div = soup0.find('div', attrs={'class':'fmcon'})
link = div.find('a', href=True)
current_issue_url = link['href']
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)
for div_cover in soup.findAll('img', {'src' : re.compile('.')}):
if re.search('\d{4}-\d{2}-\d{2}', div_cover['src']):
self.current_issue_cover = div_cover['src']
coverimg = soup.find('div', {'class': 'zzfm_img'})
self.current_issue_cover = coverimg.find('img')['src']
feeds = []
for section in soup.findAll('div', attrs={'class':'cebd'}):
section_title = self.tag_to_string(section.find('div', attrs={'class':'ceti'}))
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('a', href=True):
if re.search('\d{4}-\d{2}-\d{2}', post['href']):
date = re.search('\d{4}-\d{2}-\d{2}', post['href']).group(0)
id = re.search('\d{9}', post['href']).group(0)
url = re.sub(r'\d.*', 'templates/inc/chargecontent2.jsp?id=', post['href'])
url = url + id + '&time=' + date + '&cl=106&page=all'
for post in section.findAll('div',
attrs={'class': re.compile(r'(fmwz_bt|zzlm_nr_bt)')}):
title = self.tag_to_string(post)
articles.append({'title':title, 'url':url, 'date':date})
url = post.find('a')['href']
articles.append({'title': title, 'url': url, 'date': None})
if articles:
feeds.append((section_title, articles))