Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 10:14:46 -04:00
Code Issues Packages Projects Releases Wiki Activity

Updated New York Review of Books profile

Browse Source
This commit is contained in:
Kovid Goyal 2007-11-30 22:26:20 +00:00
parent e4c8bb6ad1
commit e5ce6adad4
1 changed files with 4 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
src/libprs500/ebooks/lrf/web/profiles/newyorkreview.py
View File

@ -1,3 +1,6 @@
## By Lorenzo goehr, lorenzogoehr@hotmail.com for Libprs500 by Kovid Goyal
from libprs500.ebooks.lrf.web.profiles import DefaultProfile from libprs500.ebooks.lrf.web.profiles import DefaultProfile
import re import re
@ -17,7 +20,5 @@ class NewYorkReviewOfBooks(DefaultProfile):
(r'<meta http-equiv="Content-Type" content="text/html; charset=(\S+)"', lambda match : match.group().replace(match.group(1), 'UTF-8')), (r'<meta http-equiv="Content-Type" content="text/html; charset=(\S+)"', lambda match : match.group().replace(match.group(1), 'UTF-8')),
(r'<body.*?((<div id="article_body">)|(<div id="st-page-maincontent">)|(<div id="containermain">)|(<p class="ap-story-p">)|(<!-- img_nav -->))', lambda match: '<body><div>'), (r'<body.*?((<div id="article_body">)|(<div id="st-page-maincontent">)|(<div id="containermain">)|(<p class="ap-story-p">)|(<!-- img_nav -->))', lambda match: '<body><div>'),
(r'((<!-- end article content -->)|(<div id="st-custom-afterpagecontent">)|(<p class="ap-story-p">&copy;)|(<div class="entry-footer">)|(<div id="see_also">)|(<p>Via <a href=)|(<div id="ss_nav">)).*?</html>', lambda match : '</div></body></html>'), (r'((<!-- end article content -->)|(<div id="st-custom-afterpagecontent">)|(<p class="ap-story-p">&copy;)|(<div class="entry-footer">)|(<div id="see_also">)|(<p>Via <a href=)|(<div id="ss_nav">)).*?</html>', lambda match : '</div></body></html>'),
(r'<a.*?onclick.*?>.*?(<img .*?>)', lambda match: match.group(1),),
(r'<div class="nav">.*?<h2>', lambda match: '<h2>'), (r'<div class="nav">.*?<h2>', lambda match: '<h2>'),
] ] (r'<table.*?>.*?(<img .*?/table>)', lambda match: match.group(1),), ] ]