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

Merge branch 'master' of https://github.com/t3d/calibre

Browse Source
This commit is contained in:
Kovid Goyal 2014-02-18 08:34:31 +05:30
commit 95f551f52f
1 changed files with 9 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
recipes/gosc_full.recipe
View File

@ -10,9 +10,9 @@ import re
from lxml import html from lxml import html
class GN(BasicNewsRecipe): class GN(BasicNewsRecipe):
__author__ = 'Piotr Kontek, Tomasz Długosz' __author__ = 'Piotr Kontek, Tomasz Długosz'
title = u'Gość Niedzielny - pełny numer' title = u'Gość Niedzielny - pełny numer'
publisher = 'Wydawnictwo Kurii Metropolitalnej w Katowicach'
description = 'Ogólnopolski tygodnik katolicki - pełny numer sprzed 4 tygodni' description = 'Ogólnopolski tygodnik katolicki - pełny numer sprzed 4 tygodni'
encoding = 'utf-8' encoding = 'utf-8'
no_stylesheets = True no_stylesheets = True
@ -28,7 +28,7 @@ class GN(BasicNewsRecipe):
def parse_index(self): def parse_index(self):
soup = self.index_to_soup('http://gosc.pl' + self.find_last_issue()) soup = self.index_to_soup('http://gosc.pl' + self.find_last_issue())
#self.masthead = 'http://www.gosc.pl' + soup.find('div',attrs={'class':'fl-w100 release-wp'}).findAll('a')[-4].contents[0]['src'] self.cover_url = 'http://www.gosc.pl' + soup.find('div',attrs={'class':'fl-w100 release-wp'}).findAll('a')[-4].contents[0]['src']
feeds = [] feeds = []
# wstepniak # wstepniak
a = soup.find('div',attrs={'class':'release-wp-b'}).find('a') a = soup.find('div',attrs={'class':'release-wp-b'}).find('a')
@ -74,6 +74,10 @@ class GN(BasicNewsRecipe):
def postprocess_html(self, soup, first_fetch): def postprocess_html(self, soup, first_fetch):
for r in soup.findAll(attrs={'class':'pgr'}): for r in soup.findAll(attrs={'class':'pgr'}):
r.extract() r.extract()
for r in soup.findAll(attrs={'class':['di_dr', 'doc_image']}):
del r['style']
for r in soup.findAll(attrs={'class':'cm-i-a'}):
r.replaceWith( r.prettify() + '<div style="clear:both"></div>')
return soup return soup
keep_only_tags = [ keep_only_tags = [
@ -81,7 +85,7 @@ class GN(BasicNewsRecipe):
] ]
remove_tags = [ remove_tags = [
dict(name='p', attrs={'class':['r tr', 'l l-2', 'wykop']}), dict(name='p', attrs={'class':['r tr', 'l l-2', 'wykop', 'tags']}),
dict(name='div', attrs={'class':['doc_actions', 'cf', 'fr1_cl']}), dict(name='div', attrs={'class':['doc_actions', 'cf', 'fr1_cl']}),
dict(name='div', attrs={'id':'vote'}), dict(name='div', attrs={'id':'vote'}),
dict(name='a', attrs={'class':'img_enlarge'}) dict(name='a', attrs={'class':'img_enlarge'})
@ -90,6 +94,6 @@ class GN(BasicNewsRecipe):
extra_css = ''' extra_css = '''
h1 {font-size:150%} h1 {font-size:150%}
p.limiter {font-size:150%; font-weight: bold} p.limiter {font-size:150%; font-weight: bold}
span.cm-i-a {text-transform:uppercase;} span.cm-i-a {text-transform:uppercase;font-size:50%}
span.cm-i-p {font-style:italic; font-size:70%} span.cm-i-p {font-style:italic; font-size:70%;text-align:right}
''' '''