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

Update Fortune Magazine

Browse Source
This commit is contained in:
Kovid Goyal 2018-04-01 09:16:24 +05:30
parent 146b3373eb
commit 2d9a45db03
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 33 additions and 53 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

86
recipes/fortune_magazine.recipe
View File

@ -1,5 +1,10 @@
from calibre.web.feeds.recipes import BasicNewsRecipe from calibre.web.feeds.recipes import BasicNewsRecipe
from collections import OrderedDict
def classes(classes):
q = frozenset(classes.split(' '))
return dict(attrs={
'class': lambda x: x and frozenset(x.split()).intersection(q)})
class Fortune(BasicNewsRecipe): class Fortune(BasicNewsRecipe):
@ -11,20 +16,24 @@ class Fortune(BasicNewsRecipe):
language = 'en' language = 'en'
category = 'news' category = 'news'
encoding = 'UTF-8' encoding = 'UTF-8'
keep_only_tags = [dict(attrs={'id': ['storycontent']})] keep_only_tags = [
remove_tags = [ dict(name='h1', attrs={'class': lambda x: x and 'headline' in x}),
dict(attrs={'class': ['hed_side', 'socialMediaToolbarContainer']})] classes('lead-media author'),
dict(id='article-body'),
]
no_javascript = True no_javascript = True
no_stylesheets = True no_stylesheets = True
needs_subscription = True needs_subscription = 'optional'
def get_browser(self): def get_browser(self):
br = BasicNewsRecipe.get_browser(self) br = BasicNewsRecipe.get_browser(self)
br.open('http://fortune.com') if self.username and self.password:
br.select_form(id='sign-in-form') br.open('http://fortune.com')
br['username'] = self.username br.select_form(id='sign-in-form')
br['password'] = self.password br['username'] = self.username
br.submit() br['password'] = self.password
br.submit()
return br return br
def parse_index(self): def parse_index(self):
@ -32,48 +41,19 @@ class Fortune(BasicNewsRecipe):
# Go to the latestissue # Go to the latestissue
soup = self.index_to_soup('http://fortune.com/section/magazine/') soup = self.index_to_soup('http://fortune.com/section/magazine/')
# Find cover & date
cover_item = soup.find('div', attrs={'id': 'cover-story'})
cover = cover_item.find('img', src=True)
self.cover_url = cover['src']
date = self.tag_to_string(cover_item.find(
'div', attrs={'class': 'tocDate'})).strip()
self.timefmt = u' [%s]' % date
feeds = OrderedDict()
section_title = ''
# checkout the cover story
articles = [] articles = []
coverstory = soup.find('div', attrs={'class': 'cnnHeadline'})
title = self.tag_to_string(coverstory.a).strip()
url = coverstory.a['href']
desc = self.tag_to_string(coverstory.findNext(
'p', attrs={'class': 'cnnBlurbTxt'}))
articles.append({'title': title, 'url': url,
'description': desc, 'date': ''})
feeds['Cover Story'] = []
feeds['Cover Story'] += articles
for post in soup.findAll('div', attrs={'class': 'cnnheader'}): for i, article in enumerate(soup.findAll('article', attrs={'class': lambda x: x and 'type-article' in x.split()})):
section_title = self.tag_to_string(post).strip() div = article.find('div', attrs={'class': lambda x: x and 'article-info' in x.split()})
articles = [] a = div.find('a', href=True)
url = a['href']
ul = post.findNext('ul') if url.startswith('/'):
for link in ul.findAll('li'): url = 'http://fortune.com' + url
links = link.find('h2') title = self.tag_to_string(a)
title = self.tag_to_string(links.a).strip() ai = div.find('div', attrs={'class': lambda x: x and 'article-info-extended' in x.split()})
url = links.a['href'] desc = ''
desc = self.tag_to_string( if ai:
link.find('p', attrs={'class': 'cnnBlurbTxt'})) desc = self.tag_to_string(desc)
articles.append({'title': title, 'url': url, self.log('Article:', title, 'at', url)
'description': desc, 'date': ''}) articles.append({'title': title, 'url': url, 'description': desc})
return [('Articles', articles)]
if articles:
if section_title not in feeds:
feeds[section_title] = []
feeds[section_title] += articles
ans = [(key, val) for key, val in feeds.iteritems()]
return ans