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

Updated recipe for New York Review of Books

Browse Source
This commit is contained in:
Kovid Goyal 2009-11-09 09:16:32 -07:00
parent b1f3bf61c7
commit a6c4b0ca47
1 changed files with 33 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
resources/recipes/new_york_review_of_books_no_sub.recipe
View File

@ -17,9 +17,37 @@ class NewYorkReviewOfBooks(BasicNewsRecipe):
description = u'Book reviews' description = u'Book reviews'
language = 'en' language = 'en'
__author__ = 'Kovid Goyal' __author__ = 'Kovid Goyal and Sujata Raman'
no_stylesheets = True
no_javascript = True
remove_tags_before = {'id':'container'} remove_tags_before = {'id':'container'}
remove_tags = [{'class':['noprint', 'ad', 'footer']}, {'id':'right-content'}] remove_tags = [{'class':['noprint', 'ad', 'footer']}, {'id':'right-content'},
dict(name='img', attrs={'src':"/images/1x1-clear.gif"}),
]
extra_css = '''
p{font-family:"Times New Roman",Georgia,serif; font-size: 60%;}
.caption{ font-family:"Times New Roman",Georgia,serif; font-size:40%;}
h2{font-family:"Times New Roman",Georgia,serif; font-size:90%;}
a{ color:#003399; }
.reviewed-title{font-family:"Times New Roman",Georgia,serif;font-size : 50%; font-style:italic;}
.reviewed-author{font-family:"Times New Roman",Georgia,serif;font-size : 50%;}
.reviewed-info{font-family:"Times New Roman",Georgia,serif;font-size : 50%;}
h5{font-family:"Times New Roman",Georgia,serif;font-size : 50%;}
.date{font-family:"Times New Roman",Georgia,serif;font-variant:small-caps;font-size : 50%;}
h4{font-family:"Times New Roman",Georgia,serif;font-size : 50%;}
'''
def preprocess_html(self, soup):
for tag in soup.findAll(name=['span',]):
tag.name = 'div'
for tag in soup.findAll(name=['blockquote',]):
tag.name = 'p'
return soup
def parse_index(self): def parse_index(self):
root = html.fromstring(self.browser.open('http://www.nybooks.com/current-issue').read()) root = html.fromstring(self.browser.open('http://www.nybooks.com/current-issue').read())