diff --git a/test/tests.json b/test/tests.json index e4ea0b41e..fd9d33332 100644 --- a/test/tests.json +++ b/test/tests.json @@ -299,5 +299,14 @@ "url": "http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html", "file": "13601338388002.mp4", "md5": "85b90ccc9d73b4acd9138d3af4c27f89" + }, + { + "name": "Spiegel", + "url": "http://www.spiegel.de/video/vulkan-tungurahua-in-ecuador-ist-wieder-aktiv-video-1259285.html", + "file": "1259285.mp4", + "md5": "2c2754212136f35fb4b19767d242f66e", + "info_dict": { + "title": "Vulkanausbruch in Ecuador: Der \"Feuerschlund\" ist wieder aktiv" + } } ] diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index baba4a9a2..44b4c4376 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -126,8 +126,14 @@ class InfoExtractor(object): def _download_webpage(self, url_or_request, video_id, note=None, errnote=None): """ Returns the data of the page as a string """ urlh = self._request_webpage(url_or_request, video_id, note, errnote) + content_type = urlh.headers.get('Content-Type', '') + m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type) + if m: + encoding = m.group(1) + else: + encoding = 'utf-8' webpage_bytes = urlh.read() - return webpage_bytes.decode('utf-8', 'replace') + return webpage_bytes.decode(encoding, 'replace') class YoutubeIE(InfoExtractor): @@ -4090,6 +4096,40 @@ class MySpassIE(InfoExtractor): } return [info] +class SpiegelIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P[0-9]+)(?:\.html)?$' + + def _real_extract(self, url): + m = re.match(self._VALID_URL, url) + video_id = m.group('videoID') + + webpage = self._download_webpage(url, video_id) + m = re.search(r'
(.*?)
', webpage) + if not m: + raise ExtractorError(u'Cannot find title') + video_title = unescapeHTML(m.group(1)) + + xml_url = u'http://video2.spiegel.de/flash/' + video_id + u'.xml' + xml_code = self._download_webpage(xml_url, video_id, + note=u'Downloading XML', errnote=u'Failed to download XML') + + idoc = xml.etree.ElementTree.fromstring(xml_code) + last_type = idoc[-1] + filename = last_type.findall('./filename')[0].text + duration = float(last_type.findall('./duration')[0].text) + + video_url = 'http://video2.spiegel.de/flash/' + filename + video_ext = filename.rpartition('.')[2] + info = { + 'id': video_id, + 'url': video_url, + 'ext': video_ext, + 'title': video_title, + 'duration': duration, + } + return [info] + + def gen_extractors(): """ Return a list of an instance of every supported extractor. The order does matter; the first extractor matched is the one handling the URL. @@ -4138,6 +4178,7 @@ def gen_extractors(): KeekIE(), TEDIE(), MySpassIE(), + SpiegelIE(), GenericIE() ]