Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-11-03 19:17:02 -05:00
Code Issues Packages Projects Releases Wiki Activity

Sync to trunk.

Browse Source
This commit is contained in:
John Schember 2010-01-14 06:54:29 -05:00
commit e31fc920db
1 changed files with 26 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
resources/recipes/nejm.recipe
View File

@ -1,3 +1,4 @@
# -*- coding: utf-8 -*-
from calibre.web.feeds.recipes import BasicNewsRecipe
class NYTimes(BasicNewsRecipe):
@ -9,21 +10,17 @@ class NYTimes(BasicNewsRecipe):
needs_subscription = True
no_stylesheets = True
#remove_tags_before = dict(name='h1', attrs={'class':'heading'})
#remove_tags_after = dict(name='td', attrs={'class':'newptool1'})
remove_tags_before = dict(name='div', attrs={'align':'center'})
remove_tags_after = dict(name='ol', attrs={'compact':'COMPACT'})
remove_tags = [
dict(name='iframe'),
#dict(name='div', attrs={'class':'related-articles'}),
#dict(name='div', attrs={'id':['qrformdiv', 'inSection', 'alpha-inner']}),
dict(name='form', attrs={'onsubmit':"return verifySearch(this.w,'Keyword, citation, or author')"}),
dict(name='table', attrs={'cellspacing':'0'}),
dict(name='div', attrs={'id':['sidebar']}),
#dict(name='form', attrs={'onsubmit':"return verifySearch(this.w,'Keyword, citation, or author')"}),
dict(name='table', attrs={'align':'RIGHT'}),
]
def preprocess_html(self, soup):
table = soup.find('table')
if table is not None:
table.extract()
return soup
#TO LOGIN
def get_browser(self):
@ -44,9 +41,9 @@ class NYTimes(BasicNewsRecipe):
# To parse artice toc
def parse_index(self):
soup = self.nejm_get_index()
parse_soup = self.nejm_get_index()
div = soup.find(id='centerTOC')
div = parse_soup.find(id='centerTOC')
current_section = None
current_articles = []
@ -81,3 +78,20 @@ class NYTimes(BasicNewsRecipe):
return feeds
def preprocess_html(self, soup):
for a in soup.findAll(text=lambda x: x and '[in this window]' in x):
a = a.findParent('a')
url = a.get('href', None)
if not url:
continue
if url.startswith('/'):
url = 'http://content.nejm.org'+url
isoup = self.index_to_soup(url)
img = isoup.find('img', src=lambda x: x and
x.startswith('/content/'))
if img is not None:
img.extract()
table = a.findParent('table')
table.replaceWith(img)
return soup