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

Fix #1773 (WSJ recipe hangs at 100%)

Browse Source
This commit is contained in:
Kovid Goyal 2009-02-04 15:55:11 -08:00
parent 5dc2e18f7d
commit 6c93872167
1 changed files with 8 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
src/calibre/web/feeds/recipes/recipe_wsj.py
View File

@ -15,11 +15,12 @@ class WallStreetJournal(BasicNewsRecipe):
needs_subscription = True needs_subscription = True
max_articles_per_feed = 10 max_articles_per_feed = 10
timefmt = ' [%a, %b %d, %Y]' timefmt = ' [%a, %b %d, %Y]'
html2lrf_options = ['--ignore-tables'] no_stylesheets = True
remove_tags_before = dict(name='h1') remove_tags_before = dict(name='h1')
remove_tags = [ remove_tags = [
dict(id=["articleTabs_tab_article", "articleTabs_tab_comments", "articleTabs_tab_interactive"]), dict(id=["articleTabs_tab_article", "articleTabs_tab_comments", "articleTabs_tab_interactive"]),
{'class':['more_in', "insetContent", 'articleTools_bottom', 'aTools', "tooltip", "adSummary", "nav-inline"]}, {'class':['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"},] remove_tags_after = [dict(id="article_story_body"), {'class':"article story"},]
@ -34,6 +35,11 @@ class WallStreetJournal(BasicNewsRecipe):
br.submit() br.submit()
return br return br
def postprocess_html(self, soup, first):
for tag in soup.findAll(name=['table', 'tr', 'td']):
tag.name = 'div'
return soup
def get_article_url(self, article): def get_article_url(self, article):
try: try:
return article.feedburner_origlink.split('?')[0] return article.feedburner_origlink.split('?')[0]
@ -43,8 +49,7 @@ class WallStreetJournal(BasicNewsRecipe):
def cleanup(self): def cleanup(self):
self.browser.open('http://online.wsj.com/logout?url=http://online.wsj.com') self.browser.open('http://online.wsj.com/logout?url=http://online.wsj.com')
def get_feeds(self): feeds = [
return [
#('Most Emailed - Day', 'http://online.wsj.com/xml/rss/3_7030.xml'), #('Most Emailed - Day', 'http://online.wsj.com/xml/rss/3_7030.xml'),
#('Most Emailed - Week', 'http://online.wsj.com/xml/rss/3_7253.xml'), #('Most Emailed - Week', 'http://online.wsj.com/xml/rss/3_7253.xml'),
#('Most Emailed - Month', 'http://online.wsj.com/xml/rss/3_7254.xml'), #('Most Emailed - Month', 'http://online.wsj.com/xml/rss/3_7254.xml'),