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

Fix #5848 (WSJ error downloading)

Browse Source
This commit is contained in:
Kovid Goyal 2010-06-16 10:44:26 -06:00
parent 05aa76c149
commit d596bf55ba
1 changed files with 104 additions and 100 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

94
resources/recipes/wsj.recipe
View File

@ -3,9 +3,8 @@ __license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
__docformat__ = 'restructuredtext en'
import string
from calibre.web.feeds.news import BasicNewsRecipe
from calibre import strftime
# http://online.wsj.com/page/us_in_todays_paper.html
@ -72,56 +71,61 @@ class WallStreetJournal(BasicNewsRecipe):
def parse_index(self):
soup = self.wsj_get_index()
year = strftime('%Y')
for x in soup.findAll('td', height='25', attrs={'class':'b14'}):
txt = self.tag_to_string(x).strip()
txt = txt.replace(u'\xa0', ' ')
txt = txt.encode('ascii', 'ignore')
if year in txt:
self.timefmt = ' [%s]'%txt
break
date = soup.find('span', attrs={'class':'date-date'})
if date is not None:
self.timefmt = ' [%s]'%self.tag_to_string(date)
left_column = soup.find(
text=lambda t: 'begin ITP Left Column' in str(t))
table = left_column.findNext('table')
current_section = None
current_articles = []
feeds = []
for x in table.findAllNext(True):
if x.name == 'td' and x.get('class', None) == 'b13':
if current_articles and current_section:
feeds.append((current_section, current_articles))
current_section = self.tag_to_string(x.a).strip()
current_articles = []
self.log('\tProcessing section:', current_section)
if current_section is not None and x.name == 'a' and \
x.get('class', None) == 'bold80':
title = self.tag_to_string(x)
url = x.get('href', False)
if not url or not title:
continue
url = url.partition('#')[0]
sections = {}
sec_order = []
for a in soup.findAll('a', attrs={'class':'mjLinkItem'}, href=True):
container = a.findParent(['li', 'div'])
if container.name == 'div':
section = 'Page One'
else:
section = ''
sec = container.find('a', href=lambda x: x and '/search?' in x)
if sec is not None:
section = self.tag_to_string(sec).strip()
if not section:
h = container.find(['h1','h2','h3','h4','h5','h6'])
section = self.tag_to_string(h)
section = string.capitalize(section).replace('U.s.', 'U.S.')
if section not in sections:
sections[section] = []
sec_order.append(section)
meta = a.find(attrs={'class':'meta_sectionName'})
if meta is not None:
meta.extract()
title = self.tag_to_string(a).strip() + ' [%s]'%self.tag_to_string(meta)
url = 'http://online.wsj.com'+a['href']
desc = ''
d = x.findNextSibling(True)
if d is not None and d.get('class', None) == 'arialResize':
desc = self.tag_to_string(d)
desc = desc.partition(u'\u2022')[0]
self.log('\t\tFound article:', title)
self.log('\t\t\t', url)
if url.startswith('/'):
url = 'http://online.wsj.com'+url
if desc:
self.log('\t\t\t', desc)
current_articles.append({'title': title, 'url':url,
p = container.find('p')
if p is not None:
desc = self.tag_to_string(p)
sections[section].append({'title':title, 'url':url,
'description':desc, 'date':''})
if current_articles and current_section:
feeds.append((current_section, current_articles))
self.log('Found article:', title)
a.extract()
for a in container.findAll('a', href=lambda x: x and '/article/'
in x):
url = a['href']
if not url.startswith('http:'):
url = 'http://online.wsj.com'+url
title = self.tag_to_string(a).strip()
if not title or title.startswith('['): continue
if title:
sections[section].append({'title':self.tag_to_string(a),
'url':url, 'description':'', 'date':''})
self.log('\tFound related:', title)
feeds = [(sec, sections[sec]) for sec in sec_order]
return feeds
def cleanup(self):
self.browser.open('http://online.wsj.com/logout?url=http://online.wsj.com')