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

Download cover for New Yorker

Browse Source
This commit is contained in:
Kovid Goyal 2014-07-28 08:07:19 +05:30
parent 5881287671
commit 77f1223202
1 changed files with 6 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
recipes/new_yorker.recipe
View File

@ -7,7 +7,6 @@ from calibre.web.feeds.news import BasicNewsRecipe
class NewYorker(BasicNewsRecipe): class NewYorker(BasicNewsRecipe):
title = u'New Yorker Magazine' title = u'New Yorker Magazine'
newyorker_prefix = 'http://m.newyorker.com'
description = u'Content from the New Yorker website' description = u'Content from the New Yorker website'
masthead_url = 'http://www.newyorker.com/images/elements/print/newyorker_printlogo.gif' masthead_url = 'http://www.newyorker.com/images/elements/print/newyorker_printlogo.gif'
@ -30,18 +29,15 @@ class NewYorker(BasicNewsRecipe):
.caption { font-size: xx-small; font-style: italic; font-weight: normal; } .caption { font-size: xx-small; font-style: italic; font-weight: normal; }
''' '''
def get_cover_url(self):
cover_url = "http://www.newyorker.com/images/covers/1925/1925_02_21_p233.jpg"
soup = self.index_to_soup('http://www.newyorker.com/magazine?intcid=magazine')
cover_item = soup.find('div',attrs={'id':'media-count-1'})
if cover_item:
cover_url = 'http://www.newyorker.com' + cover_item.div.img['src'].strip()
return cover_url
def parse_index(self): def parse_index(self):
soup = self.index_to_soup('http://www.newyorker.com/magazine?intcid=magazine') soup = self.index_to_soup('http://www.newyorker.com/magazine?intcid=magazine')
ph = soup.find('div', attrs={'class':lambda x: x and 'cover-info' in x.split()})
if ph is not None:
img = ph.find('img', src=True)
if img is not None:
self.cover_url = img['src'].replace('-320.jpg', '.jpg')
articles = [] articles = []
for story in soup.findAll('article', attrs={'itemtype':'http://schema.org/NewsArticle'}): for story in soup.findAll('article', itemtype='http://schema.org/NewsArticle'):
h2 = story.find('h2') h2 = story.find('h2')
url = h2.find('a', href=True)['href'] url = h2.find('a', href=True)['href']
a = h2.find('a') a = h2.find('a')