diff options
author | remitamine <remitamine@gmail.com> | 2015-12-31 16:35:51 +0100 |
---|---|---|
committer | remitamine <remitamine@gmail.com> | 2015-12-31 16:35:51 +0100 |
commit | 9d46608efabe25454288b5decaa96f9216506770 (patch) | |
tree | 42bf2b20c764996a353ed5510feee850cc9603e1 /youtube_dl | |
parent | 80b8b72cb847bd286eea01819bf43fd8bbe6aa92 (diff) | |
download | youtube-dl-9d46608efabe25454288b5decaa96f9216506770.tar.xz |
[ora] Add new extractor(closes #7732)
Diffstat (limited to 'youtube_dl')
-rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
-rw-r--r-- | youtube_dl/extractor/ora.py | 75 |
2 files changed, 76 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index abfabc7da..3df80bf00 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -491,6 +491,7 @@ from .ooyala import ( OoyalaIE, OoyalaExternalIE, ) +from .ora import OraTVIE from .orf import ( ORFTVthekIE, ORFOE1IE, diff --git a/youtube_dl/extractor/ora.py b/youtube_dl/extractor/ora.py new file mode 100644 index 000000000..9c4255a2d --- /dev/null +++ b/youtube_dl/extractor/ora.py @@ -0,0 +1,75 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re +from .common import InfoExtractor +from ..compat import compat_urlparse +from ..utils import ( + get_element_by_attribute, + qualities, + unescapeHTML, +) + + +class OraTVIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?ora\.tv/([^/]+/)*(?P<id>[^/\?#]+)' + _TEST = { + 'url': 'https://www.ora.tv/larrykingnow/2015/12/16/vine-youtube-stars-zach-king-king-bach-on-their-viral-videos-0_36jupg6090pq', + 'md5': 'fa33717591c631ec93b04b0e330df786', + 'info_dict': { + 'id': '50178', + 'ext': 'mp4', + 'title': 'Vine & YouTube Stars Zach King & King Bach On Their Viral Videos!', + 'description': 'md5:ebbc5b1424dd5dba7be7538148287ac1', + 'duration': 1477, + } + } + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + + video_data = self._search_regex( + r'"current"\s*:\s*({[^}]+?})', webpage, 'current video') + m3u8_url = self._search_regex( + r'"hls_stream"\s*:\s*"([^"]+)', video_data, 'm3u8 url', None) + if m3u8_url: + formats = self._extract_m3u8_formats( + m3u8_url, display_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False) + # simular to GameSpotIE + m3u8_path = compat_urlparse.urlparse(m3u8_url).path + QUALITIES_RE = r'((,[a-z]+\d+)+,?)' + available_qualities = self._search_regex( + QUALITIES_RE, m3u8_path, 'qualities').strip(',').split(',') + http_path = m3u8_path[1:].split('/', 1)[1] + http_template = re.sub(QUALITIES_RE, r'%s', http_path) + http_template = http_template.replace('.csmil/master.m3u8', '') + http_template = compat_urlparse.urljoin( + 'http://videocdn-pmd.ora.tv/', http_template) + preference = qualities( + ['mobile400', 'basic400', 'basic600', 'sd900', 'sd1200', 'sd1500', 'hd720', 'hd1080']) + for q in available_qualities: + formats.append({ + 'url': http_template % q, + 'format_id': q, + 'preference': preference(q), + }) + self._sort_formats(formats) + else: + return self.url_result(self._search_regex( + r'"youtube_id"\s*:\s*"([^"]+)', webpage, 'youtube id'), 'Youtube') + + return { + 'id': self._search_regex( + r'"video_id"\s*:\s*(\d+)', video_data, 'video id'), + 'display_id': display_id, + 'title': unescapeHTML(self._og_search_title(webpage)), + 'description': get_element_by_attribute( + 'class', 'video_txt_decription', webpage), + 'thumbnail': self._proto_relative_url(self._search_regex( + r'"thumb"\s*:\s*"([^"]+)', video_data, 'thumbnail', None)), + 'duration': int(self._search_regex( + r'"duration"\s*:\s*(\d+)', video_data, 'duration')), + 'formats': formats, + } |