X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/e8cd8c4bd832446f1971215b9fedc4531555dc1a..2ed70d87eb852121963682cc3227f3bab9079714:/youtube_dl/extractor/spiegel.py diff --git a/youtube_dl/extractor/spiegel.py b/youtube_dl/extractor/spiegel.py index 051a34d..340a384 100644 --- a/youtube_dl/extractor/spiegel.py +++ b/youtube_dl/extractor/spiegel.py @@ -1,3 +1,6 @@ +# encoding: utf-8 +from __future__ import unicode_literals + import re from .common import InfoExtractor @@ -6,20 +9,35 @@ from .common import InfoExtractor class SpiegelIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P[0-9]+)(?:\.html)?(?:#.*)?$' _TESTS = [{ - u'url': u'http://www.spiegel.de/video/vulkan-tungurahua-in-ecuador-ist-wieder-aktiv-video-1259285.html', - u'file': u'1259285.mp4', - u'md5': u'2c2754212136f35fb4b19767d242f66e', - u'info_dict': { - u"title": u"Vulkanausbruch in Ecuador: Der \"Feuerschlund\" ist wieder aktiv" - } - }, - { - u'url': u'http://www.spiegel.de/video/schach-wm-videoanalyse-des-fuenften-spiels-video-1309159.html', - u'file': u'1309159.mp4', - u'md5': u'f2cdf638d7aa47654e251e1aee360af1', - u'info_dict': { - u'title': u'Schach-WM in der Videoanalyse: Carlsen nutzt die Fehlgriffe des Titelverteidigers' - } + 'url': 'http://www.spiegel.de/video/vulkan-tungurahua-in-ecuador-ist-wieder-aktiv-video-1259285.html', + 'md5': '2c2754212136f35fb4b19767d242f66e', + 'info_dict': { + 'id': '1259285', + 'ext': 'mp4', + 'title': 'Vulkanausbruch in Ecuador: Der "Feuerschlund" ist wieder aktiv', + 'description': 'md5:8029d8310232196eb235d27575a8b9f4', + 'duration': 49, + }, + }, { + 'url': 'http://www.spiegel.de/video/schach-wm-videoanalyse-des-fuenften-spiels-video-1309159.html', + 'md5': 'f2cdf638d7aa47654e251e1aee360af1', + 'info_dict': { + 'id': '1309159', + 'ext': 'mp4', + 'title': 'Schach-WM in der Videoanalyse: Carlsen nutzt die Fehlgriffe des Titelverteidigers', + 'description': 'md5:c2322b65e58f385a820c10fa03b2d088', + 'duration': 983, + }, + }, { + 'url': 'http://www.spiegel.de/video/johann-westhauser-videobotschaft-des-hoehlenforschers-video-1502367.html', + 'md5': '54f58ba0e752e3c07bc2a26222dd0acf', + 'info_dict': { + 'id': '1502367', + 'ext': 'mp4', + 'title': 'Videobotschaft: Höhlenforscher Westhauser dankt seinen Rettern', + 'description': 'md5:c6f1ec11413ebd1088b6813943e5fc91', + 'duration': 42, + }, }] def _real_extract(self, url): @@ -28,18 +46,20 @@ class SpiegelIE(InfoExtractor): webpage = self._download_webpage(url, video_id) - video_title = self._html_search_regex( - r'
(.*?)
', webpage, u'title') + title = self._html_search_regex( + r'
(.*?)
', webpage, 'title') + description = self._html_search_meta('description', webpage, 'description') + + base_url = self._search_regex( + r'var\s+server\s*=\s*"([^"]+)\"', webpage, 'server URL') - xml_url = u'http://video2.spiegel.de/flash/' + video_id + u'.xml' - idoc = self._download_xml( - xml_url, video_id, - note=u'Downloading XML', errnote=u'Failed to download XML') + xml_url = base_url + video_id + '.xml' + idoc = self._download_xml(xml_url, video_id) formats = [ { 'format_id': n.tag.rpartition('type')[2], - 'url': u'http://video2.spiegel.de/flash/' + n.find('./filename').text, + 'url': base_url + n.find('./filename').text, 'width': int(n.find('./width').text), 'height': int(n.find('./height').text), 'abr': int(n.find('./audiobitrate').text), @@ -55,10 +75,10 @@ class SpiegelIE(InfoExtractor): self._sort_formats(formats) - info = { + return { 'id': video_id, - 'title': video_title, + 'title': title, + 'description': description, 'duration': duration, 'formats': formats, } - return info