mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
134 lines
4.1 KiB
Python
134 lines
4.1 KiB
Python
#!/usr/bin/env python
|
|
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2011, Davide Cavalca <davide125 at tiscali.it>'
|
|
'''
|
|
lwn.net
|
|
'''
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
from calibre.ebooks.BeautifulSoup import BeautifulSoup
|
|
import re
|
|
|
|
class WeeklyLWN(BasicNewsRecipe):
|
|
title = 'LWN.net Weekly Edition'
|
|
description = 'Weekly summary of what has happened in the free software world.'
|
|
__author__ = 'Davide Cavalca'
|
|
language = 'en'
|
|
site_url = 'http://lwn.net'
|
|
|
|
extra_css = 'pre,code,samp,kbd,tt { font-size: 80% }\nblockquote {margin-left:0 }\n* { color: black }\n'
|
|
|
|
cover_url = site_url + '/images/lcorner.png'
|
|
#masthead_url = 'http://lwn.net/images/lcorner.png'
|
|
publication_type = 'magazine'
|
|
|
|
remove_tags_before = dict(attrs={'class':'PageHeadline'})
|
|
remove_tags_after = dict(attrs={'class':'ArticleText'})
|
|
remove_tags = [dict(name=['h2', 'form'])]
|
|
|
|
preprocess_regexps = [
|
|
# Remove the <hr> and "Log in to post comments"
|
|
(re.compile(r'<hr.*?comments[)]', re.DOTALL), lambda m: ''),
|
|
]
|
|
|
|
conversion_options = { 'linearize_tables' : True }
|
|
|
|
oldest_article = 7.0
|
|
needs_subscription = 'optional'
|
|
|
|
def get_browser(self):
|
|
br = BasicNewsRecipe.get_browser()
|
|
if self.username is not None and self.password is not None:
|
|
br.open('https://lwn.net/login')
|
|
br.select_form(name='loginform')
|
|
br['Username'] = self.username
|
|
br['Password'] = self.password
|
|
br.submit()
|
|
return br
|
|
|
|
def print_version(self, url):
|
|
|
|
# Strip off anchor
|
|
url = url.split('#')[0]
|
|
|
|
# Prepend site_url
|
|
if url[0:len(self.site_url)] != self.site_url:
|
|
url = self.site_url + url
|
|
|
|
# Append printable URL parameter
|
|
print_param = '?format=printable'
|
|
if url[-len(print_param):] != print_param:
|
|
url += print_param
|
|
|
|
#import sys
|
|
#print >>sys.stderr, "*** print_version(url):", url
|
|
return url
|
|
|
|
def parse_index(self):
|
|
if self.username is not None and self.password is not None:
|
|
index_url = self.print_version('/current/bigpage')
|
|
else:
|
|
index_url = self.print_version('/free/bigpage')
|
|
soup = self.index_to_soup(index_url)
|
|
body = soup.body
|
|
|
|
articles = {}
|
|
ans = []
|
|
old_section = None
|
|
url_re = re.compile('^/Articles/')
|
|
|
|
while True:
|
|
tag_title = body.findNext(attrs={'class':'SummaryHL'})
|
|
if tag_title == None:
|
|
break
|
|
|
|
tag_section = tag_title.findPrevious(attrs={'class':'Cat1HL'})
|
|
if tag_section == None:
|
|
section = 'Front Page'
|
|
else:
|
|
section = tag_section.string
|
|
|
|
tag_section2 = tag_title.findPrevious(attrs={'class':'Cat2HL'})
|
|
if tag_section2 != None:
|
|
if tag_section2.findPrevious(attrs={'class':'Cat1HL'}) == tag_section:
|
|
section = "%s: %s" %(section, tag_section2.string)
|
|
|
|
if section not in articles.keys():
|
|
articles[section] = []
|
|
if section not in ans:
|
|
ans.append(section)
|
|
|
|
body = tag_title
|
|
while True:
|
|
tag_url = body.findNext(name='a', attrs={'href':url_re})
|
|
if tag_url == None:
|
|
break
|
|
body = tag_url
|
|
if tag_url.string == None:
|
|
continue
|
|
elif tag_url.string == 'Full Story':
|
|
break
|
|
elif tag_url.string.startswith('Comments ('):
|
|
break
|
|
else:
|
|
continue
|
|
|
|
if tag_url == None:
|
|
break
|
|
|
|
|
|
article = dict(
|
|
title=self.tag_to_string(tag_title),
|
|
url=tag_url['href'],
|
|
description='', content='', date='')
|
|
articles[section].append(article)
|
|
|
|
ans = [(key, articles[key]) for key in ans if articles.has_key(key)]
|
|
if not ans:
|
|
raise Exception('Could not find any articles.')
|
|
|
|
return ans
|
|
|
|
# vim: expandtab:ts=4:sw=4
|