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

Improved recipe for the Time magazine

Browse Source
This commit is contained in:
Kovid Goyal 2009-06-30 08:14:29 -06:00
parent 5cfe7571a4
commit b5b195b5f2
1 changed files with 99 additions and 95 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

194
src/calibre/web/feeds/recipes/recipe_time_magazine.py
View File

@ -1,95 +1,99 @@
#!/usr/bin/env python #!/usr/bin/env python
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2008, Kovid Goyal <kovid@kovidgoyal.net>'
''' '''
time.com time.com
''' '''
import re import re
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class Time(BasicNewsRecipe): class Time(BasicNewsRecipe):
title = u'Time' title = u'Time'
__author__ = 'Kovid Goyal' __author__ = 'Kovid Goyal and Sujata Raman'
description = 'Weekly magazine' description = 'Weekly magazine'
encoding = 'utf-8' encoding = 'utf-8'
no_stylesheets = True no_stylesheets = True
language = _('English') language = _('English')
extra_css = '''.headline {font-size: large;}
remove_tags_before = dict(id="artHd") .fact { padding-top: 10pt }
remove_tags_after = {'class':"ltCol"} h1 {font-family:Arial,Sans-serif}
remove_tags = [ .byline{font-family:Arial,Sans-serif; font-size:xx-small ;color:blue}
{'class':['articleTools', 'enlarge', 'search']}, .timestamp{font-family:Arial,Sans-serif; font-size:x-small ;color:gray}'''
{'id':['quigoArticle', 'contentTools', 'articleSideBar', 'header', 'navTop']}, remove_tags_before = dict(id="artHd")
{'target':'_blank'}, remove_tags_after = {'class':"ltCol"}
] remove_tags = [
recursions = 1 {'class':['articleTools', 'enlarge', 'search','socialtools','blogtools','moretools','page','nextUp','next','subnav','RSS','line2','first','ybuzz','articlePagination','chiclets','imgcont','createListLink','rlinks','tabsWrap','pagination']},
match_regexps = [r'/[0-9,]+-(2|3|4|5|6|7|8|9)(,\d+){0,1}.html'] {'id':['quigoArticle', 'contentTools', 'articleSideBar', 'header', 'navTop','articleTools','feedmodule','feedmodule3','promos','footer','linksFooter','timeArchive','belt','relatedStories','packages','Features']},
{'target':'_blank'},
]
def parse_index(self): recursions = 1
soup = self.index_to_soup('http://www.time.com/time/magazine') match_regexps = [r'/[0-9,]+-(2|3|4|5|6|7|8|9)(,\d+){0,1}.html']
img = soup.find('a', title="View Large Cover", href=True)
if img is not None:
cover_url = 'http://www.time.com'+img['href'] def parse_index(self):
try: soup = self.index_to_soup('http://www.time.com/time/magazine')
nsoup = self.index_to_soup(cover_url) img = soup.find('a', title="View Large Cover", href=True)
img = nsoup.find('img', src=re.compile('archive/covers')) if img is not None:
if img is not None: cover_url = 'http://www.time.com'+img['href']
self.cover_url = img['src'] try:
except: nsoup = self.index_to_soup(cover_url)
self.log.exception('Failed to fetch cover') img = nsoup.find('img', src=re.compile('archive/covers'))
if img is not None:
self.cover_url = img['src']
feeds = [] except:
parent = soup.find(id='tocGuts') self.log.exception('Failed to fetch cover')
for seched in parent.findAll(attrs={'class':'toc_seched'}):
section = self.tag_to_string(seched).capitalize()
articles = list(self.find_articles(seched)) feeds = []
feeds.append((section, articles)) parent = soup.find(id='tocGuts')
for seched in parent.findAll(attrs={'class':'toc_seched'}):
return feeds section = self.tag_to_string(seched).capitalize()
articles = list(self.find_articles(seched))
def find_articles(self, seched): feeds.append((section, articles))
for a in seched.findNextSiblings('a', href=True, attrs={'class':'toc_hed'}):
yield { return feeds
'title' : self.tag_to_string(a),
'url' : 'http://www.time.com'+a['href'], def find_articles(self, seched):
'date' : '', for a in seched.findNextSiblings('a', href=True, attrs={'class':'toc_hed'}):
'description' : self.article_description(a) yield {
} 'title' : self.tag_to_string(a),
'url' : 'http://www.time.com'+a['href'],
def article_description(self, a): 'date' : '',
ans = [] 'description' : self.article_description(a)
while True: }
t = a.nextSibling
if t is None: def article_description(self, a):
break ans = []
a = t while True:
if getattr(t, 'name', False): t = a.nextSibling
if t.get('class', '') == 'toc_parens' or t.name == 'br': if t is None:
continue break
if t.name in ('div', 'a'): a = t
break if getattr(t, 'name', False):
ans.append(self.tag_to_string(t)) if t.get('class', '') == 'toc_parens' or t.name == 'br':
else: continue
ans.append(unicode(t)) if t.name in ('div', 'a'):
return u' '.join(ans).replace(u'\xa0', u'').strip() break
ans.append(self.tag_to_string(t))
def postprocess_html(self, soup, first_page): else:
div = soup.find(attrs={'class':'artPag'}) ans.append(unicode(t))
if div is not None: return u' '.join(ans).replace(u'\xa0', u'').strip()
div.extract()
if not first_page: def postprocess_html(self, soup, first_page):
for cls in ('photoBkt', 'artHd'): div = soup.find(attrs={'class':'artPag'})
div = soup.find(attrs={'class':cls}) if div is not None:
if div is not None: div.extract()
div.extract() if not first_page:
div = soup.find(attrs={'class':'artTxt'}) for cls in ('photoBkt', 'artHd'):
if div is not None: div = soup.find(attrs={'class':cls})
p = div.find('p') if div is not None:
if p is not None: div.extract()
p.extract() div = soup.find(attrs={'class':'artTxt'})
if div is not None:
return soup p = div.find('p')
if p is not None:
p.extract()
return soup