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 #916488 (New Updated recipe for nespaper Novi list - printed edition)

Browse Source
This commit is contained in:
Kovid Goyal 2012-01-15 08:08:27 +05:30
parent 00653e3646
commit de2d315c24
1 changed files with 21 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

41
recipes/novilist_novine_hr.recipe
View File

@ -22,13 +22,16 @@ class NoviList_hr(BasicNewsRecipe):
language = 'hr' language = 'hr'
remove_empty_feeds = True remove_empty_feeds = True
publication_type = 'newspaper' publication_type = 'newspaper'
needs_subscription = 'required' needs_subscription = True
masthead_url = 'http://novine.novilist.hr/images/system/novilist-logo.jpg' masthead_url = 'http://novine.novilist.hr/images/system/novilist-logo.jpg'
index = 'http://novine.novilist.hr/'
extra_css = """ extra_css = """
body{font-family: Geneva,Arial,Helvetica,Swiss,sans-serif } @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)}
body{font-family: Geneva,Arial,Helvetica,Swiss,sans1,sans-serif }
img{display:block; margin-bottom: 0.4em; margin-top: 0.4em} img{display:block; margin-bottom: 0.4em; margin-top: 0.4em}
.nadnaslov,.podnaslov{font-size: small; text-align: center} .nadnaslov,.podnaslov{font-size: small; display: block; margin-bottom: 1em}
.naslov{font-size: x-large; color: maroon; font-weight: bold} .naslov{font-size: x-large; color: maroon; font-weight: bold; display: block; margin-bottom: 1em;}
p{display: block}
""" """
preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')] preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
@ -47,12 +50,12 @@ class NoviList_hr(BasicNewsRecipe):
] ]
remove_tags = [dict(name=['meta', 'link', 'iframe', 'embed', 'object'])] remove_tags = [dict(name=['meta', 'link', 'iframe', 'embed', 'object'])]
remove_attributes=['border', 'lang'] remove_attributes=['border', 'lang', 'size', 'face', 'bgcolor']
def get_browser(self): def get_browser(self):
br = BasicNewsRecipe.get_browser() br = BasicNewsRecipe.get_browser()
if self.username is not None and self.password is not None: if self.username is not None and self.password is not None:
br.open('http://novine.novilist.hr/loginnow.asp') br.open(self.index + 'loginnow.asp')
br.select_form(nr=0) br.select_form(nr=0)
br['username'] = self.username br['username'] = self.username
br['password'] = self.password br['password'] = self.password
@ -62,11 +65,11 @@ class NoviList_hr(BasicNewsRecipe):
def parse_index(self): def parse_index(self):
articles = [] articles = []
count = 0 count = 0
soup = self.index_to_soup('http://novine.novilist.hr/') soup = self.index_to_soup(self.index)
#cover url #cover url
for alink in soup.findAll('a'): for alink in soup.findAll('a'):
if alink['href'].startswith('images/clanci/DOC_'): if alink['href'].startswith('images/clanci/DOC_'):
self.cover_url = 'http://novine.novilist.hr/' + alink['href'] self.cover_url = self.index + alink['href']
#feeds #feeds
for item in soup.findAll('td',attrs={'class':'tocrubrika'}): for item in soup.findAll('td',attrs={'class':'tocrubrika'}):
count = count +1 count = count +1
@ -74,28 +77,24 @@ class NoviList_hr(BasicNewsRecipe):
return articles return articles
aitem = item.a aitem = item.a
section = self.tag_to_string(aitem) section = self.tag_to_string(aitem)
feedlink = 'http://novine.novilist.hr/' + aitem['href'] feedlink = self.index + aitem['href']
feedpage = self.index_to_soup(feedlink) feedpage = self.index_to_soup(feedlink)
self.report_progress(0, _('Fetching feed')+' %s...'%(section)) self.report_progress(0, _('Fetching feed')+' %s...'%(section))
inarts = [] inarts = []
for alink in feedpage.findAll('a',attrs={'class':'naslovlinkdesno'}): for alink in feedpage.findAll('a',attrs={'class':'naslovlinkdesno'}):
url = 'http://novine.novilist.hr/' + alink['href'] url = self.index + alink['href']
title = self.tag_to_string(alink)
date = strftime(self.timefmt)
description = ''
inarts.append({ inarts.append({
'title' :title 'title' :self.tag_to_string(alink)
,'date' :date ,'date' :strftime(self.timefmt)
,'url' :url ,'url' :url
,'description':description ,'description':''
}) })
if self.remove_empty_feeds:
if inarts:
articles.append((section,inarts))
else:
articles.append((section,inarts)) articles.append((section,inarts))
return articles return articles
def print_version(self, url): def print_version(self, url):
return url.replace('?WCI=Rubrike&','?WCI=Pretrazivac&') return url.replace('?WCI=Rubrike&','?WCI=Pretrazivac&')
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return soup