mollusk/youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

+unicode_literals

Browse Source
This commit is contained in:
Philipp Hagemeister
2014-01-07 09:41:13 +01:00
parent 3d3538e422
commit ecfef3e5bf
2 changed files with 52 additions and 47 deletions
Download Patch File Download Diff File Expand all files Collapse all files

37
youtube_dl/extractor/imdb.py
View File

@@ -1,3 +1,5 @@
from __future__ import unicode_literals
import re
import json
@@ -9,18 +11,18 @@ from ..utils import (
class ImdbIE(InfoExtractor):
IE_NAME = u'imdb'
IE_DESC = u'Internet Movie Database trailers'
IE_NAME = 'imdb'
IE_DESC = 'Internet Movie Database trailers'
_VALID_URL = r'http://(?:www|m)\.imdb\.com/video/imdb/vi(?P<id>\d+)'
_TEST = {
u'url': u'http://www.imdb.com/video/imdb/vi2524815897',
u'md5': u'9f34fa777ade3a6e57a054fdbcb3a068',
u'info_dict': {
u'id': u'2524815897',
u'ext': u'mp4',
u'title': u'Ice Age: Continental Drift Trailer (No. 2) - IMDb',
u'description': u'md5:9061c2219254e5d14e03c25c98e96a81',
'url': 'http://www.imdb.com/video/imdb/vi2524815897',
'md5': '9f34fa777ade3a6e57a054fdbcb3a068',
'info_dict': {
'id': '2524815897',
'ext': 'mp4',
'title': 'Ice Age: Continental Drift Trailer (No. 2) - IMDb',
'description': 'md5:9061c2219254e5d14e03c25c98e96a81',
}
}
@@ -37,10 +39,10 @@ class ImdbIE(InfoExtractor):
f_path = f_path.strip()
format_page = self._download_webpage(
compat_urlparse.urljoin(url, f_path),
u'Downloading info for %s format' % f_id)
'Downloading info for %s format' % f_id)
json_data = self._search_regex(
r'<script[^>]+class="imdb-player-data"[^>]*?>(.*?)</script>',
format_page, u'json data', flags=re.DOTALL)
format_page, 'json data', flags=re.DOTALL)
info = json.loads(json_data)
format_info = info['videoPlayerObject']['video']
formats.append({
@@ -56,9 +58,10 @@ class ImdbIE(InfoExtractor):
'thumbnail': format_info['slate'],
}
class ImdbListIE(InfoExtractor):
IE_NAME = u'imdb:list'
IE_DESC = u'Internet Movie Database lists'
IE_NAME = 'imdb:list'
IE_DESC = 'Internet Movie Database lists'
_VALID_URL = r'http://www\.imdb\.com/list/(?P<id>[\da-zA-Z_-]{11})'
def _real_extract(self, url):
@@ -66,13 +69,13 @@ class ImdbListIE(InfoExtractor):
list_id = mobj.group('id')
# RSS XML is sometimes malformed
rss = self._download_webpage('http://rss.imdb.com/list/%s' % list_id, list_id, u'Downloading list RSS')
list_title = self._html_search_regex(r'<title>(.*?)</title>', rss, u'list title')
rss = self._download_webpage('http://rss.imdb.com/list/%s' % list_id, list_id, 'Downloading list RSS')
list_title = self._html_search_regex(r'<title>(.*?)</title>', rss, 'list title')
# Export is independent of actual author_id, but returns 404 if no author_id is provided.
# However, passing dummy author_id seems to be enough.
csv = self._download_webpage('http://www.imdb.com/list/export?list_id=%s&author_id=ur00000000' % list_id,
list_id, u'Downloading list CSV')
list_id, 'Downloading list CSV')
entries = []
for item in csv.split('\n')[1:]:
@@ -83,4 +86,4 @@ class ImdbListIE(InfoExtractor):
if item_id.startswith('vi'):
entries.append(self.url_result('http://www.imdb.com/video/imdb/%s' % item_id, 'Imdb'))
return self.playlist_result(entries, list_id, list_title)
return self.playlist_result(entries, list_id, list_title)