From 566bda51f2d943d58fbe37d88ea0fceb8ddefea8 Mon Sep 17 00:00:00 2001 From: Yen Chi Hsuan Date: Mon, 1 Feb 2016 05:00:09 +0800 Subject: [PATCH] [bpb] Fix extraction and update tests --- youtube_dl/extractor/bpb.py | 30 +++++++++++++++++++++++++----- 1 file changed, 25 insertions(+), 5 deletions(-) diff --git a/youtube_dl/extractor/bpb.py b/youtube_dl/extractor/bpb.py index 510813f76..c28e72927 100644 --- a/youtube_dl/extractor/bpb.py +++ b/youtube_dl/extractor/bpb.py @@ -1,7 +1,13 @@ # coding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor +from ..utils import ( + js_to_json, + determine_ext, +) class BpbIE(InfoExtractor): @@ -10,7 +16,8 @@ class BpbIE(InfoExtractor): _TEST = { 'url': 'http://www.bpb.de/mediathek/297/joachim-gauck-zu-1989-und-die-erinnerung-an-die-ddr', - 'md5': '0792086e8e2bfbac9cdf27835d5f2093', + # md5 fails in Python 2.6 due to buggy server response and wrong handling of urllib2 + 'md5': 'c4f84c8a8044ca9ff68bb8441d300b3f', 'info_dict': { 'id': '297', 'ext': 'mp4', @@ -25,13 +32,26 @@ def _real_extract(self, url): title = self._html_search_regex( r'

(.*?)

', webpage, 'title') - video_url = self._html_search_regex( - r'(http://film\.bpb\.de/player/dokument_[0-9]+\.mp4)', - webpage, 'video URL') + video_info_dicts = re.findall( + r"({\s*src:\s*'http://film\.bpb\.de/[^}]+})", webpage) + + formats = [] + for video_info in video_info_dicts: + video_info = self._parse_json(video_info, video_id, transform_source=js_to_json) + quality = video_info['quality'] + video_url = video_info['src'] + formats.append({ + 'url': video_url, + 'preference': 10 if quality == 'high' else 0, + 'format_note': quality, + 'format_id': '%s-%s' % (quality, determine_ext(video_url)), + }) + + self._sort_formats(formats) return { 'id': video_id, - 'url': video_url, + 'formats': formats, 'title': title, 'description': self._og_search_description(webpage), }