0x2620/python-oxweb
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

remove BeautifulSoup from spiegel

Browse source
This commit is contained in:
j 2010-01-23 10:01:23 +11:00
parent ac06e3feb0
commit 746b355c50
1 changed files with 4 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

9
oxweb/spiegel.py
View file

@ -4,8 +4,6 @@ from datetime import datetime
import re import re
import time import time
from BeautifulSoup import BeautifulSoup
import oxlib.cache import oxlib.cache
from oxlib.html import decodeHtml, stripTags from oxlib.html import decodeHtml, stripTags
import oxlib.net import oxlib.net
@ -106,9 +104,10 @@ def getIssue(year, week):
return None return None
url = 'http://service.spiegel.de/digas/servlet/epaper?Q=SP&JG=%d&AG=%d&SE=1&AN=INHALT' % (year, week) url = 'http://service.spiegel.de/digas/servlet/epaper?Q=SP&JG=%d&AG=%d&SE=1&AN=INHALT' % (year, week)
contents = [] contents = []
soup = BeautifulSoup(oxlib.cache.readUrl(url)) data = oxlib.cache.readUrl(url)
for item in soup('a', {'href': re.compile('http://service.spiegel.de/digas/servlet/epaper\?Q=SP&JG=')}): items = re.compile('<a.?href="http://service.spiegel.de/digas/servlet/epaper\?Q=SP&JG=".?>(.*?)</a>').findall(data)
item = str(item) for item in items:
item = item[1]
page = int(re.compile('&amp;SE=(.*?)"').findall(item)[0]) page = int(re.compile('&amp;SE=(.*?)"').findall(item)[0])
title = stripTags(item).strip() title = stripTags(item).strip()
contents.append({'title': title, 'page': page}) contents.append({'title': title, 'page': page})