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

some improvements in gosc_niedzielny.recipe

Browse Source
This commit is contained in:
Tomasz Długosz 2013-03-03 01:29:24 +01:00
parent 3decd7262f
commit 5aafc45c08
1 changed files with 22 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
recipes/gosc_niedzielny.recipe
View File

@ -2,7 +2,8 @@
#!/usr/bin/env python #!/usr/bin/env python
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2011, Piotr Kontek, piotr.kontek@gmail.com' __copyright__ = '2011, Piotr Kontek, piotr.kontek@gmail.com \
2013, Tomasz Długosz, tomek3d@gmail.com'
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ptempfile import PersistentTemporaryFile from calibre.ptempfile import PersistentTemporaryFile
@ -12,9 +13,9 @@ import re
class GN(BasicNewsRecipe): class GN(BasicNewsRecipe):
EDITION = 0 EDITION = 0
__author__ = 'Piotr Kontek' __author__ = 'Piotr Kontek, Tomasz Długosz'
title = u'Gość niedzielny' title = u'Gość Niedzielny'
description = 'Weekly magazine' description = 'Ogólnopolski tygodnik katolicki'
encoding = 'utf-8' encoding = 'utf-8'
no_stylesheets = True no_stylesheets = True
language = 'pl' language = 'pl'
@ -38,17 +39,25 @@ class GN(BasicNewsRecipe):
first = True first = True
for p in main_section.findAll('p', attrs={'class':None}, recursive=False): for p in main_section.findAll('p', attrs={'class':None}, recursive=False):
if first and p.find('img') != None: if first and p.find('img') != None:
article = article + '<p>' article += '<p>'
article = article + str(p.find('img')).replace('src="/files/','src="http://www.gosc.pl/files/') article += str(p.find('img')).replace('src="/files/','src="http://www.gosc.pl/files/')
article = article + '<font size="-2">' article += '<font size="-2">'
for s in p.findAll('span'): for s in p.findAll('span'):
article = article + self.tag_to_string(s) article += self.tag_to_string(s)
article = article + '</font></p>' article += '</font></p>'
else: else:
article = article + str(p).replace('src="/files/','src="http://www.gosc.pl/files/') article += str(p).replace('src="/files/','src="http://www.gosc.pl/files/')
first = False first = False
limiter = main_section.find('p', attrs={'class' : 'limiter'})
if limiter:
article += str(limiter)
html = unicode(title) + unicode(authors) + unicode(article) html = unicode(title)
#sometimes authors are not filled in:
if authors:
html += unicode(authors) + unicode(article)
else:
html += unicode(article)
self.temp_files.append(PersistentTemporaryFile('_temparse.html')) self.temp_files.append(PersistentTemporaryFile('_temparse.html'))
self.temp_files[-1].write(html) self.temp_files[-1].write(html)
@ -65,7 +74,8 @@ class GN(BasicNewsRecipe):
if img != None: if img != None:
a = img.parent a = img.parent
self.EDITION = a['href'] self.EDITION = a['href']
self.title = img['alt'] #this was preventing kindles from moving old issues to 'Back Issues' category:
#self.title = img['alt']
self.cover_url = 'http://www.gosc.pl' + img['src'] self.cover_url = 'http://www.gosc.pl' + img['src']
if year != date.today().year or not first: if year != date.today().year or not first:
break break