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 Wall Street Journal

Browse Source
This commit is contained in:
Kovid Goyal 2015-10-11 00:09:43 +05:30
parent 24ffd08b39
commit 568726db1f
2 changed files with 31 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
recipes/wsj.recipe
View File

@ -80,7 +80,7 @@ class WSJ(JavascriptRecipe):
href = 'http://online.wsj.com' + href href = 'http://online.wsj.com' + href
return href return href
def wsj_find_articles(self, url): def wsj_find_articles(self, url, ahed=False):
root = self.index_to_soup(url) root = self.index_to_soup(url)
for x in CSSSelect('div.whatsNews-simple')(root): for x in CSSSelect('div.whatsNews-simple')(root):
@ -111,6 +111,20 @@ class WSJ(JavascriptRecipe):
self.log('\tFound article:', title) self.log('\tFound article:', title)
self.log('\t\t', desc) self.log('\t\t', desc)
if ahed:
for h2 in root.xpath('//li[@class="ahed_listitem"]/h2'):
a = h2.xpath('descendant::a')[0]
title = self.tag_to_string(a)
url = self.abs_wsj_url(a.get('href'))
desc = ''
p = h2.xpath('following-sibling::p')
if p:
desc = self.tag_to_string(p[0])
articles.append({'title':title, 'url':url, 'description':desc, 'date':''})
self.log('Found article:', title)
self.log('\t\t', desc)
return articles return articles
def wsj_find_wn_articles(self, url): def wsj_find_wn_articles(self, url):
@ -145,7 +159,7 @@ class WSJ(JavascriptRecipe):
if url.endswith('whatsnews'): if url.endswith('whatsnews'):
articles = self.wsj_find_wn_articles(url) articles = self.wsj_find_wn_articles(url)
else: else:
articles = self.wsj_find_articles(url) articles = self.wsj_find_articles(url, ahed=title == 'Front Section')
except: except:
articles = [] articles = []
if articles: if articles:

17
recipes/wsj_free.recipe
View File

@ -75,7 +75,7 @@ class WSJ(JavascriptRecipe):
href = 'http://online.wsj.com' + href href = 'http://online.wsj.com' + href
return href return href
def wsj_find_articles(self, url): def wsj_find_articles(self, url, ahed=False):
root = self.index_to_soup(url) root = self.index_to_soup(url)
for x in CSSSelect('div.whatsNews-simple')(root): for x in CSSSelect('div.whatsNews-simple')(root):
@ -106,6 +106,19 @@ class WSJ(JavascriptRecipe):
self.log('\tFound article:', title) self.log('\tFound article:', title)
self.log('\t\t', desc) self.log('\t\t', desc)
if ahed:
for h2 in root.xpath('//li[@class="ahed_listitem"]/h2'):
a = h2.xpath('descendant::a')[0]
title = self.tag_to_string(a)
url = self.abs_wsj_url(a.get('href'))
desc = ''
p = h2.xpath('following-sibling::p')
if p:
desc = self.tag_to_string(p[0])
articles.append({'title':title, 'url':url, 'description':desc, 'date':''})
self.log('Found article:', title)
self.log('\t\t', desc)
return articles return articles
def wsj_find_wn_articles(self, url): def wsj_find_wn_articles(self, url):
@ -140,7 +153,7 @@ class WSJ(JavascriptRecipe):
if url.endswith('whatsnews'): if url.endswith('whatsnews'):
articles = self.wsj_find_wn_articles(url) articles = self.wsj_find_wn_articles(url)
else: else:
articles = self.wsj_find_articles(url) articles = self.wsj_find_articles(url, ahed=title == 'Front Section')
except: except:
articles = [] articles = []
if articles: if articles: