From 96c2e3e909171d103beafd1fd88e9d6e215681c6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Fri, 13 May 2016 23:25:05 +0600 Subject: [PATCH] [imdb] Improve extraction --- youtube_dl/extractor/imdb.py | 28 +++++++++++++++++++++------- 1 file changed, 21 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/imdb.py b/youtube_dl/extractor/imdb.py index 203156229..3a2b7cec5 100644 --- a/youtube_dl/extractor/imdb.py +++ b/youtube_dl/extractor/imdb.py @@ -1,10 +1,10 @@ from __future__ import unicode_literals import re -import json from .common import InfoExtractor from ..utils import ( + mimetype2ext, qualities, ) @@ -51,13 +51,27 @@ class ImdbIE(InfoExtractor): json_data = self._search_regex( r']+class="imdb-player-data"[^>]*?>(.*?)', format_page, 'json data', flags=re.DOTALL) - info = json.loads(json_data) - format_info = info['videoPlayerObject']['video'] - f_id = format_info['ffname'] + info = self._parse_json(json_data, video_id, fatal=False) + if not info: + continue + format_info = info.get('videoPlayerObject', {}).get('video', {}) + if not format_info: + continue + video_info_list = format_info.get('videoInfoList') + if not video_info_list or not isinstance(video_info_list, list): + continue + video_info = video_info_list[0] + if not video_info or not isinstance(video_info, dict): + continue + video_url = video_info.get('videoUrl') + if not video_url: + continue + format_id = format_info.get('ffname') formats.append({ - 'format_id': f_id, - 'url': format_info['videoInfoList'][0]['videoUrl'], - 'quality': quality(f_id), + 'format_id': format_id, + 'url': video_url, + 'ext': mimetype2ext(video_info.get('videoMimeType')), + 'quality': quality(format_id), }) self._sort_formats(formats)