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

...

Browse Source
This commit is contained in:
Kovid Goyal 2010-05-08 11:00:24 -06:00
parent 8d4a502620
commit 062f943b4c
1 changed files with 24 additions and 28 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
resources/recipes/discover_magazine.recipe
View File

@ -9,7 +9,6 @@ discovermagazine.com
import re import re
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup, Tag
class DiscoverMagazine(BasicNewsRecipe): class DiscoverMagazine(BasicNewsRecipe):
@ -38,7 +37,6 @@ class DiscoverMagazine(BasicNewsRecipe):
pager = soup.find('span',attrs={'class':'next'}) pager = soup.find('span',attrs={'class':'next'})
if pager: if pager:
nexturl = pager.a['href'] nexturl = pager.a['href']
print 'nexturl is: ', nexturl
soup2 = self.index_to_soup(nexturl) soup2 = self.index_to_soup(nexturl)
texttag = soup2.find('div', attrs={'class':'articlebody'}) texttag = soup2.find('div', attrs={'class':'articlebody'})
newpos = len(texttag.contents) newpos = len(texttag.contents)
@ -48,7 +46,6 @@ class DiscoverMagazine(BasicNewsRecipe):
def preprocess_html(self, soup): def preprocess_html(self, soup):
mtag = '<meta http-equiv="Content-Language" content="en-US"/>\n<meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>' mtag = '<meta http-equiv="Content-Language" content="en-US"/>\n<meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>'
print 'soup1 is: ', soup
soup.head.insert(0,mtag) soup.head.insert(0,mtag)
self.append_page(soup, soup.body, 3) self.append_page(soup, soup.body, 3)
pager = soup.find('div',attrs={'class':'listingBar'}) pager = soup.find('div',attrs={'class':'listingBar'})
@ -67,7 +64,6 @@ class DiscoverMagazine(BasicNewsRecipe):
tag.extract() tag.extract()
for tag in soup.findAll('br'): for tag in soup.findAll('br'):
tag.extract() tag.extract()
print 'soup2 is: ', soup
return soup return soup
feeds = [ feeds = [