diff options
Diffstat (limited to 'youtube_dl/extractor')
| -rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
| -rw-r--r-- | youtube_dl/extractor/cnn.py | 10 | ||||
| -rw-r--r-- | youtube_dl/extractor/common.py | 8 | ||||
| -rw-r--r-- | youtube_dl/extractor/spiegeltv.py | 81 |
4 files changed, 94 insertions, 6 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index a19e85543..72523c54d 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -258,6 +258,7 @@ from .southparkstudios import ( from .space import SpaceIE from .spankwire import SpankwireIE from .spiegel import SpiegelIE +from .spiegeltv import SpiegeltvIE from .spike import SpikeIE from .stanfordoc import StanfordOpenClassroomIE from .steam import SteamIE diff --git a/youtube_dl/extractor/cnn.py b/youtube_dl/extractor/cnn.py index b32cb8980..dae40c136 100644 --- a/youtube_dl/extractor/cnn.py +++ b/youtube_dl/extractor/cnn.py @@ -79,8 +79,11 @@ class CNNIE(InfoExtractor): self._sort_formats(formats) - thumbnails = sorted([((int(t.attrib['height']),int(t.attrib['width'])), t.text) for t in info.findall('images/image')]) - thumbs_dict = [{'resolution': res, 'url': t_url} for (res, t_url) in thumbnails] + thumbnails = [{ + 'height': int(t.attrib['height']), + 'width': int(t.attrib['width']), + 'url': t.text, + } for t in info.findall('images/image')] metas_el = info.find('metas') upload_date = ( @@ -93,8 +96,7 @@ class CNNIE(InfoExtractor): 'id': info.attrib['id'], 'title': info.find('headline').text, 'formats': formats, - 'thumbnail': thumbnails[-1][1], - 'thumbnails': thumbs_dict, + 'thumbnails': thumbnails, 'description': info.find('description').text, 'duration': duration, 'upload_date': upload_date, diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index db472aace..49e75405e 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -92,8 +92,12 @@ class InfoExtractor(object): unique, but available before title. Typically, id is something like "4234987", title "Dancing naked mole rats", and display_id "dancing-naked-mole-rats" - thumbnails: A list of dictionaries (with the entries "resolution" and - "url") for the varying thumbnails + thumbnails: A list of dictionaries, with the following entries: + * "url" + * "width" (optional, int) + * "height" (optional, int) + * "resolution" (optional, string "{width}x{height"}, + deprecated) thumbnail: Full URL to a video thumbnail image. description: One-line video description. uploader: Full name of the video uploader. diff --git a/youtube_dl/extractor/spiegeltv.py b/youtube_dl/extractor/spiegeltv.py new file mode 100644 index 000000000..7f388aced --- /dev/null +++ b/youtube_dl/extractor/spiegeltv.py @@ -0,0 +1,81 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re +from .common import InfoExtractor + + +class SpiegeltvIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?spiegel\.tv/filme/(?P<id>[\-a-z0-9]+)' + _TEST = { + 'url': 'http://www.spiegel.tv/filme/flug-mh370/', + 'info_dict': { + 'id': 'flug-mh370', + 'ext': 'm4v', + 'title': 'Flug MH370', + 'description': 'Das Rätsel um die Boeing 777 der Malaysia-Airlines', + 'thumbnail': 're:http://.*\.jpg$', + }, + 'params': { + # rtmp download + 'skip_download': True, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + title = self._html_search_regex(r'<h1.*?>(.*?)</h1>', webpage, 'title') + + apihost = 'http://spiegeltv-ivms2-restapi.s3.amazonaws.com' + version_json = self._download_json( + '%s/version.json' % apihost, video_id, + note='Downloading version information') + version_name = version_json['version_name'] + + slug_json = self._download_json( + '%s/%s/restapi/slugs/%s.json' % (apihost, version_name, video_id), + video_id, + note='Downloading object information') + oid = slug_json['object_id'] + + media_json = self._download_json( + '%s/%s/restapi/media/%s.json' % (apihost, version_name, oid), + video_id, note='Downloading media information') + uuid = media_json['uuid'] + is_wide = media_json['is_wide'] + + server_json = self._download_json( + 'http://www.spiegel.tv/streaming_servers/', video_id, + note='Downloading server information') + server = server_json[0]['endpoint'] + + thumbnails = [] + for image in media_json['images']: + thumbnails.append({ + 'url': image['url'], + 'width': image['width'], + 'height': image['height'], + }) + + description = media_json['subtitle'] + duration = media_json['duration_in_ms'] / 1000. + + if is_wide: + format = '16x9' + else: + format = '4x3' + + url = server + 'mp4:' + uuid + '_spiegeltv_0500_' + format + '.m4v' + + return { + 'id': video_id, + 'title': title, + 'url': url, + 'ext': 'm4v', + 'description': description, + 'duration': duration, + 'thumbnails': thumbnails + }
\ No newline at end of file |