Thanks again for the reply. I customized the feeds as following(just ruled out the feeds I don't want):
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal
kovid@kovidgoyal.net'
__docformat__ = 'restructuredtext en'
from calibre.web.feeds.news import BasicNewsRecipe
#
http://online.wsj.com/page/us_in_todays_paper.html
class WallStreetJournal(BasicNewsRecipe):
title = 'The Wall Street Journal'
__author__ = 'Kovid Goyal and Sujata Raman'
description = 'News and current affairs.'
needs_subscription = True
language = 'en'
max_articles_per_feed = 10
timefmt = ' [%a, %b %d, %Y]'
no_stylesheets = True
extra_css = '''h1{color:#093D72 ; font-size:large ; font-family:Georgia,"Century Schoolbook","Times New Roman",Times,serif; }
h2{color:#474537; font-family:Georgia,"Century Schoolbook","Times New Roman",Times,serif; font-size:small; font-style:italic;}
.subhead{color:gray; font-family:Georgia,"Century Schoolbook","Times New Roman",Times,serif; font-size:small; font-style:italic;}
.insettipUnit {color:#666666; font-family:Arial,Sans-serif;font-size:xx-small }
.targetCaption{ font-size:x-small; color:#333333; font-family:Arial,Helvetica,sans-serif}
.article{font-family :Arial,Helvetica,sans-serif; font-size:x-small}
.tagline {color:#333333; font-size:xx-small}
.dateStamp {color:#666666; font-family:Arial,Helvetica,sans-serif}
h3{color:blue ;font-family:Arial,Helvetica,sans-serif; font-size:xx-small}
.byline{color:blue;font-family:Arial,Helvetica,sans-serif; font-size:xx-small}
h6{color:#333333; font-family:Georgia,"Century Schoolbook","Times New Roman",Times,serif; font-size:small;font-style:italic; }
.paperLocation{color:#666666; font-size:xx-small}'''
remove_tags_before = dict(name='h1')
remove_tags = [
dict(id=["articleTabs_tab_article", "articleTabs_tab_comments", "articleTabs_tab_interactive","articleTabs_tab_vid eo","articleTabs_tab_map","articleTabs_tab_slidesh ow"]),
{'class':['footer_columns','network','insetCol3wide','intera ctive','video','slideshow','map','insettip','inset Close','more_in', "insetContent", 'articleTools_bottom', 'aTools', "tooltip", "adSummary", "nav-inline"]},
dict(rel='shortcut icon'),
]
remove_tags_after = [dict(id="article_story_body"), {'class':"article story"},]
def get_browser(self):
br = BasicNewsRecipe.get_browser()
if self.username is not None and self.password is not None:
br.open('http://commerce.wsj.com/auth/login')
br.select_form(nr=0)
br['user'] = self.username
br['password'] = self.password
br.submit()
return br
def postprocess_html(self, soup, first):
for tag in soup.findAll(name=['table', 'tr', 'td']):
tag.name = 'div'
for tag in soup.findAll('div', dict(id=["articleThumbnail_1", "articleThumbnail_2", "articleThumbnail_3", "articleThumbnail_4", "articleThumbnail_5", "articleThumbnail_6", "articleThumbnail_7"])):
tag.extract()
return soup
def get_article_url(self, article):
try:
return article.feedburner_origlink.split('?')[0]
except AttributeError:
return article.link.split('?')[0]
def cleanup(self):
self.browser.open('http://online.wsj.com/logout?url=http://online.wsj.com')
feeds = [
('Today\'s Newspaper - Page One', 'http://online.wsj.com/xml/rss/3_7205.xml'),
('Today\'s Newspaper - Marketplace', 'http://online.wsj.com/xml/rss/3_7206.xml'),
('Today\'s Newspaper - Money & Investing', 'http://online.wsj.com/xml/rss/3_7207.xml'),
('Today\'s Newspaper - Personal Journal', 'http://online.wsj.com/xml/rss/3_7208.xml'),
('Today\'s Newspaper - Weekend Journal', 'http://online.wsj.com/xml/rss/3_7209.xml'),
]
However, I tried again with the revised feeds but still got 1600+ pages. Could you please look at it and tell me what went wrong?,