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

better zipfiles, do not fail if imdb does not return

Browse source
This commit is contained in:
j 2007-03-30 20:08:19 +00:00
parent 50157e16b6
commit 19c52e22a4
2 changed files with 14 additions and 9 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

14
scrapeit/imdb.py
View file

@ -390,12 +390,14 @@ def guess(title, director=''):
if url.startswith('http://www.imdb.com/title/tt'): if url.startswith('http://www.imdb.com/title/tt'):
return url[28:35] return url[28:35]
req = urllib2.Request(imdb_url, None, utils.DEFAULT_HEADERS) try:
u = urllib2.urlopen(req) req = urllib2.Request(imdb_url, None, utils.DEFAULT_HEADERS)
data = u.read() u = urllib2.urlopen(req)
return_url = u.url data = u.read()
u.close() return_url = u.url
u.close()
except:
return None
if return_url.startswith('http://www.imdb.com/title/tt'): if return_url.startswith('http://www.imdb.com/title/tt'):
return return_url[28:35] return return_url[28:35]
if data: if data:

9
scrapeit/opensubtitles.py
View file

@ -24,10 +24,13 @@ def getZipFileLink(opensubtitle_id):
return "http://www.opensubtitles.org/en/download/sub/%s" % opensubtitle_id return "http://www.opensubtitles.org/en/download/sub/%s" % opensubtitle_id
def downloadSubtitle(zip_link): def downloadSubtitle(zip_link):
return extractSubtitles(read_url(zip_link))
def extractSubtitles(zip_data):
srts ={} srts ={}
zip = StringIO.StringIO() z = StringIO.StringIO()
zip.write(read_url(zip_link)) z.write(zip_data)
zfile = zipfile.ZipFile(zip) zfile = zipfile.ZipFile(z)
files = zfile.namelist() files = zfile.namelist()
def is_not_nfo(file): return not file.endswith('nfo') def is_not_nfo(file): return not file.endswith('nfo')
files = filter(is_not_nfo, files) files = filter(is_not_nfo, files)