aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/imdb.py
diff options
context:
space:
mode:
authorJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>2015-10-18 14:13:06 +0200
committerJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>2015-10-18 14:13:06 +0200
commitdd67702a3ea007369109ee8e4b67043064e1f759 (patch)
treef41ef06e4889a35b77376d7bbebb46fa558cc834 /youtube_dl/extractor/imdb.py
parent4a7b79038425f614af49116edab7897f0db13e5a (diff)
[imdb] Fix extraction (fixes #7220)
Diffstat (limited to 'youtube_dl/extractor/imdb.py')
-rw-r--r--youtube_dl/extractor/imdb.py29
1 files changed, 19 insertions, 10 deletions
diff --git a/youtube_dl/extractor/imdb.py b/youtube_dl/extractor/imdb.py
index 4bb574cf3..02e1e428e 100644
--- a/youtube_dl/extractor/imdb.py
+++ b/youtube_dl/extractor/imdb.py
@@ -4,8 +4,8 @@ import re
import json
from .common import InfoExtractor
-from ..compat import (
- compat_urlparse,
+from ..utils import (
+ qualities,
)
@@ -30,24 +30,33 @@ class ImdbIE(InfoExtractor):
descr = self._html_search_regex(
r'(?s)<span itemprop="description">(.*?)</span>',
webpage, 'description', fatal=False)
- available_formats = re.findall(
- r'case \'(?P<f_id>.*?)\' :$\s+url = \'(?P<path>.*?)\'', 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<url>%s.*?)".*?>(?P<name>.*?)<' % 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'<script[^>]+class="imdb-player-data"[^>]*?>(.*?)</script>',
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['videoInfoList'][0]['videoUrl'],
+ 'quality': quality(f_id),
})
+ self._sort_formats(formats)
return {
'id': video_id,