0x2620/scrapeit
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

better little info but do not fail on imdbpro locked imdb pages

Browse source
This commit is contained in:
j 2008-03-27 16:03:53 +00:00
parent 963d95ec0d
commit f24a6ae4e7
1 changed files with 12 additions and 11 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

23
scrapeit/imdb.py
View file

@ -8,7 +8,6 @@ import re, time
import os import os
import time import time
from elementtree.ElementTree import parse, tostring
from BeautifulSoup import BeautifulSoup from BeautifulSoup import BeautifulSoup
from google import google from google import google
@ -412,16 +411,18 @@ class IMDb:
def parseReleaseinfo(self): def parseReleaseinfo(self):
soup = BeautifulSoup(self.getReleaseinfo()) soup = BeautifulSoup(self.getReleaseinfo())
for row in soup('table',{'border': '0', 'cellpadding':'2'})[0]('tr'): info = soup('table',{'border': '0', 'cellpadding':'2'})
d = row('td', {'align':'right'}) if info:
if d: for row in info[0]('tr'):
try: d = row('td', {'align':'right'})
possible_date = stripTags(str(d[0])).strip() if d:
rdate = time.strptime(possible_date, "%d %B %Y") try:
rdate = time.strftime('%Y-%m-%d', rdate) possible_date = stripTags(str(d[0])).strip()
return rdate rdate = time.strptime(possible_date, "%d %B %Y")
except: rdate = time.strftime('%Y-%m-%d', rdate)
pass return rdate
except:
pass
return None return None
def getBusiness(self, forcereload = False): def getBusiness(self, forcereload = False):