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

Updated wprost

Browse Source
This commit is contained in:
Kovid Goyal 2011-06-26 20:39:35 -06:00
parent 5cbba547f8
commit f5c8e0c264
1 changed files with 69 additions and 67 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

136
recipes/wprost.recipe
View File

@ -2,90 +2,92 @@
__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>'
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
import re import re
class Wprost(BasicNewsRecipe): 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/icons/ico_blocked.gif'
title = u'Wprost' title = u'Wprost'
__author__ = 'matek09' __author__ = 'matek09'
description = 'Weekly magazine' description = 'Weekly magazine'
encoding = 'ISO-8859-2' encoding = 'ISO-8859-2'
no_stylesheets = True no_stylesheets = True
language = 'pl' language = 'pl'
remove_javascript = True remove_javascript = True
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'}))
'''keep_only_tags =[] '''keep_only_tags =[]
keep_only_tags.append(dict(name = 'table', attrs = {'id' : 'title-table'})) keep_only_tags.append(dict(name = 'table', attrs = {'id' : 'title-table'}))
keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'div-header'})) keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'div-header'}))
keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'div-content'})) keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'div-content'}))
keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'def element-autor'}))''' keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'def element-autor'}))'''
preprocess_regexps = [(re.compile(r'style="display: none;"'), lambda match: ''), preprocess_regexps = [(re.compile(r'style="display: none;"'), lambda match: ''),
(re.compile(r'display: block;'), lambda match: '')] (re.compile(r'display: block;'), lambda match: ''),
(re.compile(r'\<td\>\<tr\>\<\/table\>'), lambda match: ''),
(re.compile(r'\<table .*?\>'), lambda match: ''),
(re.compile(r'\<tr>'), lambda match: ''),
(re.compile(r'\<td .*?\>'), lambda match: '')]
remove_tags =[]
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 = {'id' : 'content-main-column-right'}))
remove_tags =[] extra_css = '''
remove_tags.append(dict(name = 'div', attrs = {'class' : 'def element-date'})) .div-header {font-size: x-small; font-weight: bold}
remove_tags.append(dict(name = 'div', attrs = {'class' : 'def silver'})) '''
remove_tags.append(dict(name = 'div', attrs = {'id' : 'content-main-column-right'}))
extra_css = '''
.div-header {font-size: x-small; font-weight: bold}
'''
#h2 {font-size: x-large; font-weight: bold} #h2 {font-size: x-large; font-weight: bold}
def is_blocked(self, a): def is_blocked(self, a):
if a.findNextSibling('img') is None: if a.findNextSibling('img') is None:
return False return False
else: else:
return True return True
def find_last_issue(self): def find_last_issue(self):
soup = self.index_to_soup('http://www.wprost.pl/archiwum/') soup = self.index_to_soup('http://www.wprost.pl/archiwum/')
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('Zobacz spis tre.ci')})
else: else:
a = soup.find('a', attrs={'title' : re.compile('Zobacz spis tre.ci')}) a = soup.find('a', attrs={'title' : re.compile('Zobacz spis tre.ci')})
self.EDITION = a['href'].replace('/tygodnik/?I=', '') self.EDITION = a['href'].replace('/tygodnik/?I=', '')
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={'class':'main-block-s3 s3-head head-red3'}):
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)
feeds.append((section, articles)) feeds.append((section, articles))
return feeds return feeds
def find_articles(self, main_block):
for a in main_block.findAllNext( attrs={'style':['','padding-top: 15px;']}):
if a.name in "td":
break
if self.EXCLUDE_LOCKED & self.is_blocked(a):
continue
yield {
'title' : self.tag_to_string(a),
'url' : 'http://www.wprost.pl' + a['href'],
'date' : '',
'description' : ''
}
def find_articles(self, main_block):
for a in main_block.findAllNext( attrs={'style':['','padding-top: 15px;']}):
if a.name in "td":
break
if self.EXCLUDE_LOCKED & self.is_blocked(a):
continue
yield {
'title' : self.tag_to_string(a),
'url' : 'http://www.wprost.pl' + a['href'],
'date' : '',
'description' : ''
}