X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/bc5059672e222ec4df4fe3983c399c0d0fca84d5..b0a896ec15ffa8ac140881cb58f12faa812fb740:/youtube_dl/extractor/spiegel.py diff --git a/youtube_dl/extractor/spiegel.py b/youtube_dl/extractor/spiegel.py index 6955205..5bd3c00 100644 --- a/youtube_dl/extractor/spiegel.py +++ b/youtube_dl/extractor/spiegel.py @@ -1,63 +1,137 @@ +# encoding: utf-8 +from __future__ import unicode_literals + import re from .common import InfoExtractor +from ..compat import compat_urlparse +from .spiegeltv import SpiegeltvIE class SpiegelIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P[0-9]+)(?:\.html)?(?:#.*)?$' + _VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P[0-9]+)(?:-embed|-iframe)?(?:\.html)?(?:#.*)?$' _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/astronaut-alexander-gerst-von-der-iss-station-beantwortet-fragen-video-1519126-embed.html', + 'md5': 'd8eeca6bfc8f1cd6f490eb1f44695d51', + 'info_dict': { + 'id': '1519126', + 'ext': 'mp4', + 'description': 'SPIEGEL ONLINE-Nutzer durften den deutschen Astronauten Alexander Gerst über sein Leben auf der ISS-Station befragen. Hier kommen seine Antworten auf die besten sechs Fragen.', + 'title': 'Fragen an Astronaut Alexander Gerst: "Bekommen Sie die Tageszeiten mit?"', } + }, { + 'url': 'http://www.spiegel.de/video/astronaut-alexander-gerst-von-der-iss-station-beantwortet-fragen-video-1519126-iframe.html', + 'only_matching': True, }] def _real_extract(self, url): - m = re.match(self._VALID_URL, url) - video_id = m.group('videoID') + video_id = self._match_id(url) + webpage, handle = self._download_webpage_handle(url, video_id) - webpage = self._download_webpage(url, video_id) + # 302 to spiegel.tv, like http://www.spiegel.de/video/der-film-zum-wochenende-die-wahrheit-ueber-maenner-video-99003272.html + if SpiegeltvIE.suitable(handle.geturl()): + return self.url_result(handle.geturl(), 'Spiegeltv') - video_title = self._html_search_regex( - r'
(.*?)
', webpage, u'title') - - 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') - - formats = [ - { - 'format_id': n.tag.rpartition('type')[2], - 'url': u'http://video2.spiegel.de/flash/' + n.find('./filename').text, - 'width': int(n.find('./width').text), - 'height': int(n.find('./height').text), - 'abr': int(n.find('./audiobitrate').text), - 'vbr': int(n.find('./videobitrate').text), - 'vcodec': n.find('./codec').text, - 'acodec': 'MP4A', - } - for n in list(idoc) - # Blacklist type 6, it's extremely LQ and not available on the same server - if n.tag.startswith('type') and n.tag != 'type6' - ] - formats.sort(key=lambda f: f['vbr']) + title = re.sub(r'\s+', ' ', self._html_search_regex( + r'(?s)<(?:h1|div) class="module-title"[^>]*>(.*?)', + 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 = base_url + video_id + '.xml' + idoc = self._download_xml(xml_url, video_id) + + formats = [] + for n in list(idoc): + if n.tag.startswith('type') and n.tag != 'type6': + format_id = n.tag.rpartition('type')[2] + video_url = base_url + n.find('./filename').text + formats.append({ + 'format_id': format_id, + 'url': video_url, + 'width': int(n.find('./width').text), + 'height': int(n.find('./height').text), + 'abr': int(n.find('./audiobitrate').text), + 'vbr': int(n.find('./videobitrate').text), + 'vcodec': n.find('./codec').text, + 'acodec': 'MP4A', + }) duration = float(idoc[0].findall('./duration')[0].text) - info = { + self._check_formats(formats, video_id) + self._sort_formats(formats) + + return { 'id': video_id, - 'title': video_title, + 'title': title, + 'description': description, 'duration': duration, 'formats': formats, } - return info + + +class SpiegelArticleIE(InfoExtractor): + _VALID_URL = 'https?://www\.spiegel\.de/(?!video/)[^?#]*?-(?P[0-9]+)\.html' + IE_NAME = 'Spiegel:Article' + IE_DESC = 'Articles on spiegel.de' + _TESTS = [{ + 'url': 'http://www.spiegel.de/sport/sonst/badminton-wm-die-randsportart-soll-populaerer-werden-a-987092.html', + 'info_dict': { + 'id': '1516455', + 'ext': 'mp4', + 'title': 'Faszination Badminton: Nennt es bloß nicht Federball', + 'description': 're:^Patrick Kämnitz gehört.{100,}', + }, + }, { + 'url': 'http://www.spiegel.de/wissenschaft/weltall/astronaut-alexander-gerst-antwortet-spiegel-online-lesern-a-989876.html', + 'info_dict': { + + }, + 'playlist_count': 6, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + # Single video on top of the page + video_link = self._search_regex( + r'\s*.*?url\s*=\s*"([^"]+)"', + webpage) + entries = [ + self.url_result(compat_urlparse.urljoin( + self.http_scheme() + '//spiegel.de/', embed_path)) + for embed_path in embeds + ] + return self.playlist_result(entries)