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

removing debug output

Browse source
This commit is contained in:
Rolux 2008-07-06 20:13:37 +02:00
parent d17ae60f8e
commit 73ce77dc2e
1 changed files with 2 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
oxweb/movieposterdb.py
View file

@ -14,19 +14,17 @@ def getPosterUrls(imdbId):
return posterUrls return posterUrls
def parsePage(url): def parsePage(url):
print url
posterUrls = [] posterUrls = []
html = cache.getUrlUnicode(url, timeout=86400) html = cache.getUrlUnicode(url, timeout=86400)
groups = re.compile('<a href="(http://www.movieposterdb.com/group/.*?)">', re.DOTALL).findall(html) groups = re.compile('<a href="(http://www.movieposterdb.com/group/.*?)">', re.DOTALL).findall(html)
print '%s Groups' % len(groups)
for group in groups: for group in groups:
posterUrls += parsePage(group) posterUrls += parsePage(group)
posters = re.compile('<a href="(http://www.movieposterdb.com/poster/.*?)">', re.DOTALL).findall(html) posters = re.compile('<a href="(http://www.movieposterdb.com/poster/.*?)">', re.DOTALL).findall(html)
for poster in posters: for poster in posters:
print 'Poster: ' + poster
html = cache.getUrlUnicode(poster) html = cache.getUrlUnicode(poster)
posterUrls.append(findRe(html, '"(http://www.movieposterdb.com/posters/.*?\.jpg)"')) posterUrls.append(findRe(html, '"(http://www.movieposterdb.com/posters/.*?\.jpg)"'))
return posterUrls return posterUrls
if __name__ == '__main__': if __name__ == '__main__':
print getPosterUrls('0133093') print getPosterUrls('0133093')
print getPosterUrls('0060304')