X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/0cf0312991a54458a07e903da2e47e9f3c8855ae..03342304420e5daeb428ffdcc7bbd2bbfecfa61a:/youtube_dl/extractor/imdb.py?ds=sidebyside
diff --git a/youtube_dl/extractor/imdb.py b/youtube_dl/extractor/imdb.py
index f2c1c10..02e1e42 100644
--- a/youtube_dl/extractor/imdb.py
+++ b/youtube_dl/extractor/imdb.py
@@ -5,7 +5,7 @@ import json
from .common import InfoExtractor
from ..utils import (
- compat_urlparse,
+ qualities,
)
@@ -16,7 +16,6 @@ class ImdbIE(InfoExtractor):
_TEST = {
'url': 'http://www.imdb.com/video/imdb/vi2524815897',
- 'md5': '9f34fa777ade3a6e57a054fdbcb3a068',
'info_dict': {
'id': '2524815897',
'ext': 'mp4',
@@ -31,24 +30,33 @@ class ImdbIE(InfoExtractor):
descr = self._html_search_regex(
r'(?s)(.*?)',
webpage, 'description', fatal=False)
- available_formats = re.findall(
- r'case \'(?P.*?)\' :$\s+url = \'(?P.*?)\'', webpage,
- flags=re.MULTILINE)
+ player_url = 'http://www.imdb.com/video/imdb/vi%s/imdb/single' % video_id
+ player_page = self._download_webpage(
+ player_url, video_id, 'Downloading player page')
+ # the player page contains the info for the default format, we have to
+ # fetch other pages for the rest of the formats
+ extra_formats = re.findall(r'href="(?P%s.*?)".*?>(?P.*?)<' % re.escape(player_url), player_page)
+ format_pages = [
+ self._download_webpage(
+ f_url, video_id, 'Downloading info for %s format' % f_name)
+ for f_url, f_name in extra_formats]
+ format_pages.append(player_page)
+
+ quality = qualities(['SD', '480p', '720p'])
formats = []
- for f_id, f_path in available_formats:
- f_path = f_path.strip()
- format_page = self._download_webpage(
- compat_urlparse.urljoin(url, f_path),
- 'Downloading info for %s format' % f_id)
+ for format_page in format_pages:
json_data = self._search_regex(
r'',
format_page, 'json data', flags=re.DOTALL)
info = json.loads(json_data)
format_info = info['videoPlayerObject']['video']
+ f_id = format_info['ffname']
formats.append({
'format_id': f_id,
- 'url': format_info['url'],
+ 'url': format_info['videoInfoList'][0]['videoUrl'],
+ 'quality': quality(f_id),
})
+ self._sort_formats(formats)
return {
'id': video_id,