diff options
author | Remita Amine <remitamine@gmail.com> | 2016-06-30 00:21:03 +0100 |
---|---|---|
committer | Remita Amine <remitamine@gmail.com> | 2016-06-30 00:21:03 +0100 |
commit | 397b305cfe1a7ec2957331602727edb009c71e99 (patch) | |
tree | 4694740f4f75ac6a16d5458ec9e3a3d68b143e56 /youtube_dl | |
parent | e496fa50cd82877d8daeda8e29056c5d7fce2de0 (diff) |
[meta] Add new extractor(closes #8789)
Diffstat (limited to 'youtube_dl')
-rw-r--r-- | youtube_dl/extractor/extractors.py | 1 | ||||
-rw-r--r-- | youtube_dl/extractor/meta.py | 56 |
2 files changed, 57 insertions, 0 deletions
diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index eeedc675b..84c39ab48 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -425,6 +425,7 @@ from .makerschannel import MakersChannelIE from .makertv import MakerTVIE from .matchtv import MatchTVIE from .mdr import MDRIE +from .meta import METAIE from .metacafe import MetacafeIE from .metacritic import MetacriticIE from .mgoon import MgoonIE diff --git a/youtube_dl/extractor/meta.py b/youtube_dl/extractor/meta.py new file mode 100644 index 000000000..674b8d264 --- /dev/null +++ b/youtube_dl/extractor/meta.py @@ -0,0 +1,56 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + unescapeHTML, + int_or_none, + ExtractorError, +) + + +class METAIE(InfoExtractor): + _VALID_URL = r'https?://video\.meta\.ua/(?P<id>[0-9]+)' + _TEST = { + 'url': 'http://video.meta.ua/5502115.video', + 'md5': '71b6f3ee274bef16f1ab410f7f56b476', + 'info_dict': { + 'id': '5502115', + 'ext': 'mp4', + 'title': 'Sony Xperia Z camera test [HQ]', + 'description': 'Xperia Z shoots video in FullHD HDR.', + 'uploader_id': 'nomobile', + 'uploader': 'CHЁZA.TV', + 'upload_date': '20130211', + }, + 'add_ie': ['Youtube'], + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + st_html5 = self._search_regex(r"st_html5\s*=\s*'#([^']+)'", webpage, 'uppod html5 st') + json_str = '' + for i in range(0, len(st_html5), 3): + json_str += '�%s;' % st_html5[i:i + 3] + uppod_data = self._parse_json(unescapeHTML(json_str), video_id) + error = uppod_data.get('customnotfound') + if error: + raise ExtractorError('%s said: %s' % (self.IE_NAME, error), expected=True) + + video_url = uppod_data['file'] + info = { + 'id': video_id, + 'url': video_url, + 'title': uppod_data.get('comment') or self._og_search_title(webpage), + 'description': self._og_search_description(webpage), + 'thumbnail': uppod_data.get('poster') or self._og_search_thumbnail(webpage), + 'duration': int_or_none(self._og_search_property('video:duration', webpage)), + } + if 'youtube.com/' in video_url: + info.update({ + '_type': 'url_transparent', + 'ie_key': 'Youtube', + }) + return info |