Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-08-11 09:13:57 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Newsweek

Browse Source
This commit is contained in:
Kovid Goyal 2018-06-17 08:51:41 +05:30
parent d82d6f823c
commit 472fc44c70
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 31 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

49
recipes/newsweek.recipe
View File

@ -49,31 +49,44 @@ class Newsweek(BasicNewsRecipe):
img = li.xpath('descendant::a[@href]/img[@src]')[0] img = li.xpath('descendant::a[@href]/img[@src]')[0]
self.cover_url = img.get('src') self.cover_url = img.get('src')
root = self.index_to_soup(url, as_tree=True) root = self.index_to_soup(url, as_tree=True)
div = root.xpath( div = root.xpath('//div[@id="block-nw-magazine-magazine-features"]')[0]
'//div[@id="block-nw-magazine-magazine-cover-story"]')[0] features = []
a = div.xpath('descendant::a[@href]')[0] href_xpath = 'descendant::*[local-name()="h1" or local-name()="h2" or local-name()="h3" or local-name()="h4"]/a[@href]'
index = [('Cover', [{'title': 'Cover story', 'url': href_to_url(a)}])] for a in div.xpath(href_xpath):
sections = defaultdict(list)
div = root.xpath(
'//div[@id="block-nw-magazine-magazine-issue-story-list"]')[0]
for a in div.xpath('descendant::h3/a[@href and contains(@class, "article-link")]'):
title = self.tag_to_string(a) title = self.tag_to_string(a)
article = a.xpath('ancestor::article')[0] article = a.xpath('ancestor::article')[0]
desc = '' desc = ''
s = article.xpath('descendant::div[@class="summary"]') s = article.xpath('descendant::div[@class="summary"]')
if s: if s:
desc = self.tag_to_string(s[0]) desc = self.tag_to_string(s[0])
sec = article.xpath('descendant::div[@class="category"]')
if sec:
sec = self.tag_to_string(sec[0])
else:
sec = 'Articles'
sections[sec].append(
{'title': title, 'url': href_to_url(a), 'description': desc})
self.log(title, url) self.log(title, url)
if desc: features.append({'title': title, 'url': href_to_url(a), 'description': desc})
self.log('\t' + desc)
self.log('') index = []
if features:
index.append(('Features', features))
sections = defaultdict(list)
for block in ('magazine-magazine-issue-story-list', 'editors-pick'):
div = root.xpath(
'//div[@id="block-nw-{}"]'.format(block))[0]
for a in div.xpath(href_xpath):
title = self.tag_to_string(a)
article = a.xpath('ancestor::article')[0]
desc = ''
s = article.xpath('descendant::div[@class="summary"]')
if s:
desc = self.tag_to_string(s[0])
sec = article.xpath('descendant::div[@class="category"]')
if sec:
sec = self.tag_to_string(sec[0])
else:
sec = 'Articles'
sections[sec].append(
{'title': title, 'url': href_to_url(a), 'description': desc})
self.log(title, url)
if desc:
self.log('\t' + desc)
self.log('')
for k in sorted(sections): for k in sorted(sections):
index.append((k, sections[k])) index.append((k, sections[k]))
return index return index