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 Guardian

Browse Source
This commit is contained in:
Kovid Goyal 2010-10-04 14:07:44 -06:00
parent 588ce1adb8
commit fbb87d9f8a
1 changed files with 16 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
resources/recipes/guardian.recipe
View File

@ -8,10 +8,16 @@ www.guardian.co.uk
''' '''
from calibre import strftime from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
from datetime import date
class Guardian(BasicNewsRecipe): class Guardian(BasicNewsRecipe):
title = u'The Guardian' title = u'The Guardian / The Observer'
if date.today().weekday() == 6:
base_url = "http://www.guardian.co.uk/theobserver"
else:
base_url = "http://www.guardian.co.uk/theguardian"
__author__ = 'Seabound and Sujata Raman' __author__ = 'Seabound and Sujata Raman'
language = 'en_GB' language = 'en_GB'
@ -19,6 +25,10 @@ class Guardian(BasicNewsRecipe):
max_articles_per_feed = 100 max_articles_per_feed = 100
remove_javascript = True remove_javascript = True
# List of section titles to ignore
# For example: ['Sport']
ignore_sections = []
timefmt = ' [%a, %d %b %Y]' timefmt = ' [%a, %d %b %Y]'
keep_only_tags = [ keep_only_tags = [
dict(name='div', attrs={'id':["content","article_header","main-article-info",]}), dict(name='div', attrs={'id':["content","article_header","main-article-info",]}),
@ -28,6 +38,7 @@ class Guardian(BasicNewsRecipe):
dict(name='div', attrs={'id':["article-toolbox","subscribe-feeds",]}), dict(name='div', attrs={'id':["article-toolbox","subscribe-feeds",]}),
dict(name='ul', attrs={'class':["pagination"]}), dict(name='ul', attrs={'class':["pagination"]}),
dict(name='ul', attrs={'id':["content-actions"]}), dict(name='ul', attrs={'id':["content-actions"]}),
dict(name='img'),
] ]
use_embedded_content = False use_embedded_content = False
@ -43,18 +54,6 @@ class Guardian(BasicNewsRecipe):
#match-stats-summary{font-size:small; font-family:Arial,Helvetica,sans-serif;font-weight:normal;} #match-stats-summary{font-size:small; font-family:Arial,Helvetica,sans-serif;font-weight:normal;}
''' '''
feeds = [
('Front Page', 'http://www.guardian.co.uk/rss'),
('Business', 'http://www.guardian.co.uk/business/rss'),
('Sport', 'http://www.guardian.co.uk/sport/rss'),
('Culture', 'http://www.guardian.co.uk/culture/rss'),
('Money', 'http://www.guardian.co.uk/money/rss'),
('Life & Style', 'http://www.guardian.co.uk/lifeandstyle/rss'),
('Travel', 'http://www.guardian.co.uk/travel/rss'),
('Environment', 'http://www.guardian.co.uk/environment/rss'),
('Comment','http://www.guardian.co.uk/commentisfree/rss'),
]
def get_article_url(self, article): def get_article_url(self, article):
url = article.get('guid', None) url = article.get('guid', None)
if '/video/' in url or '/flyer/' in url or '/quiz/' in url or \ if '/video/' in url or '/flyer/' in url or '/quiz/' in url or \
@ -76,7 +75,8 @@ class Guardian(BasicNewsRecipe):
return soup return soup
def find_sections(self): def find_sections(self):
soup = self.index_to_soup('http://www.guardian.co.uk/theguardian') # soup = self.index_to_soup("http://www.guardian.co.uk/theobserver")
soup = self.index_to_soup(self.base_url)
# find cover pic # find cover pic
img = soup.find( 'img',attrs ={'alt':'Guardian digital edition'}) img = soup.find( 'img',attrs ={'alt':'Guardian digital edition'})
if img is not None: if img is not None:
@ -113,13 +113,10 @@ class Guardian(BasicNewsRecipe):
try: try:
feeds = [] feeds = []
for title, href in self.find_sections(): for title, href in self.find_sections():
feeds.append((title, list(self.find_articles(href)))) if not title in self.ignore_sections:
feeds.append((title, list(self.find_articles(href))))
return feeds return feeds
except: except:
raise NotImplementedError raise NotImplementedError
def postprocess_html(self,soup,first):
return soup.findAll('html')[0]