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 Newsweek

Browse Source
This commit is contained in:
Kovid Goyal 2019-06-13 16:29:45 +05:30
parent b702e94090
commit 408990ffd8
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 31 additions and 29 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
recipes/newsweek.recipe
View File

@ -49,17 +49,16 @@ class Newsweek(BasicNewsRecipe):
a = li.xpath('descendant::a[@href]')[0] a = li.xpath('descendant::a[@href]')[0]
url = href_to_url(a, add_piano=True) url = href_to_url(a, add_piano=True)
self.timefmt = self.tag_to_string(a) self.timefmt = self.tag_to_string(a)
img = li.xpath('descendant::a[@href]//img[@src]')[0] img = li.xpath('descendant::a[@href]//img[@data-src]')[0]
self.cover_url = img.get('src') self.cover_url = img.get('data-src').partition('?')[0]
root = self.index_to_soup(url, as_tree=True) root = self.index_to_soup(url, as_tree=True)
features = [] features = []
href_xpath = 'descendant::*[local-name()="h1" or local-name()="h2" or local-name()="h3" or local-name()="h4"]/a[@href]'
try: try:
div = root.xpath('//div[@id="block-nw-magazine-magazine-features"]')[0] div = root.xpath('//div[@class="magazine-features"]')[0]
except IndexError: except IndexError:
pass pass
else: else:
for a in div.xpath(href_xpath): for a in div.xpath('descendant::div[@class="h1"]//a[@href]'):
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 = ''
@ -73,12 +72,16 @@ class Newsweek(BasicNewsRecipe):
if features: if features:
index.append(('Features', features)) index.append(('Features', features))
sections = defaultdict(list) sections = defaultdict(list)
for block in ('magazine-magazine-issue-story-list', 'editors-pick'): for widget in ('editor-pick',):
div = root.xpath( self.parse_widget(widget, sections)
'//div[@id="block-nw-{}"]'.format(block)) for k in sorted(sections):
if not div: index.append((k, sections[k]))
continue return index
div = div[0]
def parse_widget(self, widget, sections):
root = self.index_to_soup('https://d.newsweek.com/widget/' + widget, as_tree=True)
div = root.xpath('//div')[0]
href_xpath = 'descendant::*[local-name()="h1" or local-name()="h2" or local-name()="h3" or local-name()="h4"]/a[@href]'
for a in div.xpath(href_xpath): for a in div.xpath(href_xpath):
title = self.tag_to_string(a) title = self.tag_to_string(a)
article = a.xpath('ancestor::article')[0] article = a.xpath('ancestor::article')[0]
@ -97,9 +100,6 @@ class Newsweek(BasicNewsRecipe):
if desc: if desc:
self.log('\t' + desc) self.log('\t' + desc)
self.log('') self.log('')
for k in sorted(sections):
index.append((k, sections[k]))
return index
def print_version(self, url): def print_version(self, url):
return url + '?piano_d=1' return url + '?piano_d=1'
@ -114,4 +114,6 @@ class Newsweek(BasicNewsRecipe):
s['style'] = 'display: block' s['style'] = 'display: block'
s.name = 'img' s.name = 'img'
s['src'] = url s['src'] = url
for img in soup.findAll('img', attrs={'data-src': True}):
img['src'] = img['data-src']
return soup return soup