diff options
author | Philipp Hagemeister <phihag@phihag.de> | 2014-08-24 01:34:28 +0200 |
---|---|---|
committer | Philipp Hagemeister <phihag@phihag.de> | 2014-08-24 01:34:28 +0200 |
commit | 30b871b0ca09ae6088d8a8a0f77bf4d25aa0cb5b (patch) | |
tree | 5f7ebe4a1029794fe8f3217bb52ebb958b54427c /youtube_dl/extractor | |
parent | eb9da9b732c63309e8592729d3e048953086a308 (diff) | |
parent | a54bda3ae2d659c9020668a638dccc3545a1ecb1 (diff) |
Merge remote-tracking branch 'origin/master'
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r-- | youtube_dl/extractor/wat.py | 67 |
1 files changed, 55 insertions, 12 deletions
diff --git a/youtube_dl/extractor/wat.py b/youtube_dl/extractor/wat.py index a584e0896..1f330378a 100644 --- a/youtube_dl/extractor/wat.py +++ b/youtube_dl/extractor/wat.py @@ -2,27 +2,30 @@ from __future__ import unicode_literals import re +import time +import hashlib from .common import InfoExtractor from ..utils import ( + ExtractorError, unified_strdate, ) class WatIE(InfoExtractor): - _VALID_URL = r'http://www\.wat\.tv/.*-(?P<shortID>.*?)_.*?\.html' + _VALID_URL = r'http://www\.wat\.tv/video/(?P<display_id>.*)-(?P<short_id>.*?)_.*?\.html' IE_NAME = 'wat.tv' _TEST = { - 'url': 'http://www.wat.tv/video/world-war-philadelphia-vost-6bv55_2fjr7_.html', + 'url': 'http://www.wat.tv/video/soupe-figues-l-orange-aux-epices-6z1uz_2hvf7_.html', + 'md5': 'ce70e9223945ed26a8056d413ca55dc9', 'info_dict': { - 'id': '10631273', + 'id': '11713067', + 'display_id': 'soupe-figues-l-orange-aux-epices', 'ext': 'mp4', - 'title': 'World War Z - Philadelphia VOST', - 'description': 'La menace est partout. Que se passe-t-il à Philadelphia ?\r\nWORLD WAR Z, avec Brad Pitt, au cinéma le 3 juillet.\r\nhttp://www.worldwarz.fr', - }, - 'params': { - # Sometimes wat serves the whole file with the --test option - 'skip_download': True, + 'title': 'Soupe de figues à l\'orange et aux épices', + 'description': 'Retrouvez l\'émission "Petits plats en équilibre", diffusée le 18 août 2014.', + 'upload_date': '20140819', + 'duration': 120, }, } @@ -36,13 +39,20 @@ class WatIE(InfoExtractor): def real_id_for_chapter(chapter): return chapter['tc_start'].split('-')[0] mobj = re.match(self._VALID_URL, url) - short_id = mobj.group('shortID') - webpage = self._download_webpage(url, short_id) + short_id = mobj.group('short_id') + display_id = mobj.group('display_id') + webpage = self._download_webpage(url, display_id or short_id) real_id = self._search_regex(r'xtpage = ".*-(.*?)";', webpage, 'real id') video_info = self.download_video_info(real_id) + + if video_info.get('geolock'): + raise ExtractorError('This content is not available in your area', expected=True) + chapters = video_info['chapters'] first_chapter = chapters[0] + files = video_info['files'] + first_file = files[0] if real_id_for_chapter(first_chapter) != real_id: self.to_screen('Multipart video detected') @@ -61,12 +71,45 @@ class WatIE(InfoExtractor): upload_date = unified_strdate(first_chapter['date_diffusion']) # Otherwise we can continue and extract just one part, we have to use # the short id for getting the video url + + formats = [{ + 'url': 'http://wat.tv/get/android5/%s.mp4' % real_id, + 'format_id': 'Mobile', + }] + + fmts = [('SD', 'web')] + if first_file.get('hasHD'): + fmts.append(('HD', 'webhd')) + + def compute_token(param): + timestamp = '%08x' % int(time.time()) + magic = '9b673b13fa4682ed14c3cfa5af5310274b514c4133e9b3a81e6e3aba009l2564' + return '%s/%s' % (hashlib.md5((magic + param + timestamp).encode('ascii')).hexdigest(), timestamp) + + for fmt in fmts: + webid = '/%s/%s' % (fmt[1], real_id) + video_url = self._download_webpage( + 'http://www.wat.tv/get%s?token=%s&getURL=1' % (webid, compute_token(webid)), + real_id, + 'Downloding %s video URL' % fmt[0], + 'Failed to download %s video URL' % fmt[0], + False) + if not video_url: + continue + formats.append({ + 'url': video_url, + 'ext': 'mp4', + 'format_id': fmt[0], + }) + return { 'id': real_id, - 'url': 'http://wat.tv/get/android5/%s.mp4' % real_id, + 'display_id': display_id, 'title': first_chapter['title'], 'thumbnail': first_chapter['preview'], 'description': first_chapter['description'], 'view_count': video_info['views'], 'upload_date': upload_date, + 'duration': first_file['duration'], + 'formats': formats, } |