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

Fix Gosc Niedzielny

Browse Source
This commit is contained in:
Kovid Goyal 2011-10-13 07:36:30 +05:30
parent 24ccb1a562
commit b6fab126dc
1 changed files with 18 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
recipes/gosc_niedzielny.recipe
View File

@ -10,16 +10,17 @@ import re
class GN(BasicNewsRecipe):
EDITION = 0
__author__ = 'Piotr Kontek'
title = u'Gość niedzielny'
title = unicode('Gość niedzielny')
description = 'Weekly magazine'
encoding = 'utf-8'
no_stylesheets = True
language = 'pl'
remove_javascript = True
temp_files = []
temp_files = []
simultaneous_downloads = 1
articles_are_obfuscated = True
def get_obfuscated_article(self, url):
@ -27,9 +28,9 @@ class GN(BasicNewsRecipe):
br.open(url)
source = br.response().read()
page = self.index_to_soup(source)
main_section = page.find('div',attrs={'class':'txt doc_prnt_prv'})
title = main_section.find('h2')
info = main_section.find('div', attrs={'class' : 'cf doc_info'})
authors = info.find(attrs={'class':'l'})
@ -41,17 +42,17 @@ class GN(BasicNewsRecipe):
article = article + str(p.find('img')).replace('src="/files/','src="http://www.gosc.pl/files/')
article = article + '<font size="-2">'
for s in p.findAll('span'):
article = article + self.tag_to_string(s)
article = article + self.tag_to_string(s)
article = article + '</font></p>'
else:
article = article + str(p).replace('src="/files/','src="http://www.gosc.pl/files/')
first = False
html = unicode(title) + unicode(authors) + unicode(article)
self.temp_files.append(PersistentTemporaryFile('_temparse.html'))
self.temp_files[-1].write(html)
self.temp_files[-1].close()
self.temp_files.append(PersistentTemporaryFile('_temparse.html'))
self.temp_files[-1].write(html)
self.temp_files[-1].close()
return self.temp_files[-1].name
def find_last_issue(self):
@ -68,7 +69,7 @@ class GN(BasicNewsRecipe):
if not first:
break
first = False
def parse_index(self):
self.find_last_issue()
soup = self.index_to_soup('http://www.gosc.pl' + self.EDITION)
@ -94,16 +95,16 @@ class GN(BasicNewsRecipe):
def find_articles(self, main_block):
for a in main_block.findAll('div', attrs={'class':'prev_doc2'}):
art = a.find('a')
yield {
art = a.find('a')
yield {
'title' : self.tag_to_string(art),
'url' : 'http://www.gosc.pl' + art['href'].replace('/doc/','/doc_pr/'),
'date' : '',
'description' : ''
}
for a in main_block.findAll('div', attrs={'class':'sr-document'}):
art = a.find('a')
yield {
art = a.find('a')
yield {
'title' : self.tag_to_string(art),
'url' : 'http://www.gosc.pl' + art['href'].replace('/doc/','/doc_pr/'),
'date' : '',