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

align to kalibrator - wprost.recipe

Browse Source
This commit is contained in:
Tomasz Długosz 2012-10-26 21:36:57 +02:00
parent 5a26d7ceb3
commit ac47781c7c
1 changed files with 15 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
recipes/wprost.recipe
View File

@ -3,6 +3,8 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2010, matek09, matek09@gmail.com' __copyright__ = '2010, matek09, matek09@gmail.com'
__copyright__ = 'Modified 2011, Mariusz Wolek <mariusz_dot_wolek @ gmail dot com>' __copyright__ = 'Modified 2011, Mariusz Wolek <mariusz_dot_wolek @ gmail dot com>'
__copyright__ = 'Modified 2012, Artur Stachecki <artur.stachecki@gmail.com>'
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
import re import re
@ -11,7 +13,7 @@ class Wprost(BasicNewsRecipe):
EDITION = 0 EDITION = 0
FIND_LAST_FULL_ISSUE = True FIND_LAST_FULL_ISSUE = True
EXCLUDE_LOCKED = True EXCLUDE_LOCKED = True
ICO_BLOCKED = 'http://www.wprost.pl/G/icons/ico_blocked.gif' ICO_BLOCKED = 'http://www.wprost.pl/G/layout2/ico_blocked.png'
title = u'Wprost' title = u'Wprost'
__author__ = 'matek09' __author__ = 'matek09'
@ -20,6 +22,7 @@ class Wprost(BasicNewsRecipe):
no_stylesheets = True no_stylesheets = True
language = 'pl' language = 'pl'
remove_javascript = True remove_javascript = True
recursions = 0
remove_tags_before = dict(dict(name = 'div', attrs = {'id' : 'print-layer'})) remove_tags_before = dict(dict(name = 'div', attrs = {'id' : 'print-layer'}))
remove_tags_after = dict(dict(name = 'div', attrs = {'id' : 'print-layer'})) remove_tags_after = dict(dict(name = 'div', attrs = {'id' : 'print-layer'}))
@ -35,13 +38,15 @@ class Wprost(BasicNewsRecipe):
(re.compile(r'\<td\>\<tr\>\<\/table\>'), lambda match: ''), (re.compile(r'\<td\>\<tr\>\<\/table\>'), lambda match: ''),
(re.compile(r'\<table .*?\>'), lambda match: ''), (re.compile(r'\<table .*?\>'), lambda match: ''),
(re.compile(r'\<tr>'), lambda match: ''), (re.compile(r'\<tr>'), lambda match: ''),
(re.compile(r'\<td .*?\>'), lambda match: '')] (re.compile(r'\<td .*?\>'), lambda match: ''),
(re.compile(r'\<div id="footer"\>.*?\</footer\>'), lambda match: '')]
remove_tags =[] remove_tags =[]
remove_tags.append(dict(name = 'div', attrs = {'class' : 'def element-date'})) remove_tags.append(dict(name = 'div', attrs = {'class' : 'def element-date'}))
remove_tags.append(dict(name = 'div', attrs = {'class' : 'def silver'})) remove_tags.append(dict(name = 'div', attrs = {'class' : 'def silver'}))
remove_tags.append(dict(name = 'div', attrs = {'id' : 'content-main-column-right'})) remove_tags.append(dict(name = 'div', attrs = {'id' : 'content-main-column-right'}))
extra_css = ''' extra_css = '''
.div-header {font-size: x-small; font-weight: bold} .div-header {font-size: x-small; font-weight: bold}
''' '''
@ -59,27 +64,26 @@ class Wprost(BasicNewsRecipe):
a = 0 a = 0
if self.FIND_LAST_FULL_ISSUE: if self.FIND_LAST_FULL_ISSUE:
ico_blocked = soup.findAll('img', attrs={'src' : self.ICO_BLOCKED}) ico_blocked = soup.findAll('img', attrs={'src' : self.ICO_BLOCKED})
a = ico_blocked[-1].findNext('a', attrs={'title' : re.compile('Zobacz spis tre.ci')}) a = ico_blocked[-1].findNext('a', attrs={'title' : re.compile(r'Spis *', re.IGNORECASE | re.DOTALL)})
else: else:
a = soup.find('a', attrs={'title' : re.compile('Zobacz spis tre.ci')}) a = soup.find('a', attrs={'title' : re.compile(r'Spis *', re.IGNORECASE | re.DOTALL)})
self.EDITION = a['href'].replace('/tygodnik/?I=', '') self.EDITION = a['href'].replace('/tygodnik/?I=', '')
self.EDITION_SHORT = a['href'].replace('/tygodnik/?I=15', '')
self.cover_url = a.img['src'] self.cover_url = a.img['src']
def parse_index(self): def parse_index(self):
self.find_last_issue() self.find_last_issue()
soup = self.index_to_soup('http://www.wprost.pl/tygodnik/?I=' + self.EDITION) soup = self.index_to_soup('http://www.wprost.pl/tygodnik/?I=' + self.EDITION)
feeds = [] feeds = []
for main_block in soup.findAll(attrs={'class':'main-block-s3 s3-head head-red3'}): for main_block in soup.findAll(attrs={'id': 'content-main-column-element-content'}):
articles = list(self.find_articles(main_block)) articles = list(self.find_articles(main_block))
if len(articles) > 0: if len(articles) > 0:
section = self.tag_to_string(main_block) section = self.tag_to_string(main_block.find('h3'))
feeds.append((section, articles)) feeds.append((section, articles))
return feeds return feeds
def find_articles(self, main_block): def find_articles(self, main_block):
for a in main_block.findAllNext( attrs={'style':['','padding-top: 15px;']}): for a in main_block.findAll('a'):
if a.name in "td": if a.name in "td":
break break
if self.EXCLUDE_LOCKED & self.is_blocked(a): if self.EXCLUDE_LOCKED & self.is_blocked(a):
@ -91,3 +95,4 @@ class Wprost(BasicNewsRecipe):
'description' : '' 'description' : ''
} }