mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-09 03:04:10 -04:00
IGN:Split new guardian recipe into sections
This commit is contained in:
Kovid Goyal
parent
7f4365e159
commit
ab72fba13b
BIN
resources/images/news/guardian.png
Normal file
BIN
resources/images/news/guardian.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 548 B |
@ -6,7 +6,10 @@ __docformat__ = 'restructuredtext en'
|
||||
'''
|
||||
www.guardian.co.uk
|
||||
'''
|
||||
|
||||
import string
|
||||
import re
|
||||
from calibre import strftime
|
||||
from calibre.ebooks.BeautifulSoup import BeautifulSoup, Tag
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class Guardian(BasicNewsRecipe):
|
||||
@ -42,101 +45,101 @@ class Guardian(BasicNewsRecipe):
|
||||
#full-contents{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):
|
||||
# url = article.get('guid', None)
|
||||
# if '/video/' in url or '/flyer/' in url or '/quiz/' in url or \
|
||||
# '/gallery/' in url or 'ivebeenthere' in url or \
|
||||
# 'pickthescore' in url or 'audioslideshow' in url :
|
||||
# url = None
|
||||
# return url
|
||||
|
||||
def parse_index(self):
|
||||
|
||||
articles = []
|
||||
|
||||
|
||||
|
||||
def parse_index(self):
|
||||
|
||||
soup = self.index_to_soup('http://www.guardian.co.uk/theguardian')
|
||||
# find cover pic
|
||||
img = soup.find( 'img',attrs ={'alt':'Guardian digital edition'})
|
||||
|
||||
if img is not None:
|
||||
self.cover_url = img['src']
|
||||
|
||||
img = soup.find( 'img',attrs ={'alt':'Guardian digital edition'})
|
||||
if img is None: return None
|
||||
else:
|
||||
self.cover_url = img['src']
|
||||
# end find cover pic
|
||||
sections = []
|
||||
ans = []
|
||||
for li in soup.findAll( 'li'):
|
||||
|
||||
if li.a and li.a.has_key('href'):
|
||||
url = li.a['href']
|
||||
if 'mainsection' in url:
|
||||
|
||||
|
||||
#find the articles in the Main Section
|
||||
|
||||
section = ''
|
||||
articles = []
|
||||
|
||||
if li.a and li.a.has_key('href'):
|
||||
url = li.a['href']
|
||||
if 'mainsection' in url:
|
||||
section = self.tag_to_string(url)
|
||||
i = len(section)
|
||||
|
||||
index1 = section.rfind('/',0,i)
|
||||
section = section[index1+1:i]
|
||||
sections.append(section)
|
||||
|
||||
#find the articles in the Main Section start
|
||||
soup = self.index_to_soup(url)
|
||||
|
||||
date = strftime('%a, %d %b')
|
||||
descl = []
|
||||
|
||||
for desclist in soup.findAll(name='div',attrs={'class':"trailtext"}):
|
||||
descl.append(self.tag_to_string(desclist).strip())
|
||||
|
||||
t = -1
|
||||
for tag in soup.findAll('h3'):
|
||||
t = t+1
|
||||
|
||||
for a in tag.findAll('a'):
|
||||
|
||||
if a and a.has_key('href'):
|
||||
|
||||
url2 = a['href']
|
||||
|
||||
|
||||
if t < len(descl):
|
||||
desc = descl[t]
|
||||
else:
|
||||
url2 =''
|
||||
|
||||
desc = ''
|
||||
if a and a.has_key('href'):
|
||||
url2 = a['href']
|
||||
else:
|
||||
url2 =''
|
||||
title = self.tag_to_string(a)
|
||||
#eliminate duplicates
|
||||
if len(articles) == 0:
|
||||
desc = 'Main Section'
|
||||
date = ''
|
||||
articles.append({
|
||||
|
||||
if len(articles) == 0: #First article
|
||||
|
||||
articles.append({
|
||||
'title':title,
|
||||
'date':date,
|
||||
'url':url2,
|
||||
'description':desc,
|
||||
})
|
||||
else:
|
||||
if len(articles) > 0:
|
||||
if {'title':title,'date':date,'url':url2,'description':desc} in articles:
|
||||
ulrl2 = ''
|
||||
#eliminate duplicates
|
||||
else:
|
||||
|
||||
desc = 'Main Section'
|
||||
date = ''
|
||||
articles.append({
|
||||
#eliminate duplicates start
|
||||
if {'title':title,'date':date,'url':url2,'description':desc} in articles :
|
||||
url2 = ''
|
||||
#eliminate duplicates end
|
||||
else:
|
||||
if 'http://jobs.guardian.co.uk/' in url2:
|
||||
url2 = ''
|
||||
else:
|
||||
|
||||
articles.append({
|
||||
'title':title,
|
||||
'date':date,
|
||||
'url':url2,
|
||||
'description':desc,
|
||||
})
|
||||
#find the articles in the Main Section
|
||||
else:
|
||||
url =''
|
||||
|
||||
|
||||
|
||||
|
||||
return [('Current Issue', articles)]
|
||||
|
||||
'description':desc,
|
||||
})
|
||||
#find the articles in the Main Section end
|
||||
ans.append( articles)
|
||||
|
||||
else:
|
||||
url =''
|
||||
|
||||
|
||||
titles = map(self.find_title, sections)
|
||||
ans1 = list(zip(titles,ans))
|
||||
|
||||
return ans1[2:]
|
||||
|
||||
def find_title(self, section):
|
||||
d = {'topstories':'Top Stories', 'international':'International', 'editorialsandreply':'Editorials and Reply',
|
||||
'commentanddebate':'Comment and Debate','uknews':'UK News','saturday':'Saturday','sunday':'Sunday',
|
||||
'reviews':'Reviews', 'obituaries':'Obituaries'}
|
||||
|
||||
return d.get(section, section)
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
|
||||
|
||||
for item in soup.findAll(style=True):
|
||||
del item['style']
|
||||
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user