# coding: utf-8
+from __future__ import unicode_literals
-import json
import re
+import hashlib
from .common import InfoExtractor
-
-from ..utils import (
- unified_strdate,
-)
+from ..utils import 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 = {
- u'url': u'http://www.wat.tv/video/world-war-philadelphia-vost-6bv55_2fjr7_.html',
- u'file': u'10631273.mp4',
- u'md5': u'd8b2231e1e333acd12aad94b80937e19',
- u'info_dict': {
- u'title': u'World War Z - Philadelphia VOST',
- u'description': u'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',
+ _TESTS = [
+ {
+ 'url': 'http://www.wat.tv/video/soupe-figues-l-orange-aux-epices-6z1uz_2hvf7_.html',
+ 'md5': 'ce70e9223945ed26a8056d413ca55dc9',
+ 'info_dict': {
+ 'id': '11713067',
+ 'display_id': 'soupe-figues-l-orange-aux-epices',
+ 'ext': 'mp4',
+ '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,
+ },
+ },
+ {
+ 'url': 'http://www.wat.tv/video/gregory-lemarchal-voix-ange-6z1v7_6ygkj_.html',
+ 'md5': 'fbc84e4378165278e743956d9c1bf16b',
+ 'info_dict': {
+ 'id': '11713075',
+ 'display_id': 'gregory-lemarchal-voix-ange',
+ 'ext': 'mp4',
+ 'title': 'Grégory Lemarchal, une voix d\'ange depuis 10 ans (1/3)',
+ 'description': 'md5:b7a849cf16a2b733d9cd10c52906dee3',
+ 'upload_date': '20140816',
+ 'duration': 2910,
+ },
},
- u'skip': u'Sometimes wat serves the whole file with the --test option',
- }
-
+ ]
+
def download_video_info(self, real_id):
# 'contentv4' is used in the website, but it also returns the related
# videos, we don't need them
- info = self._download_webpage('http://www.wat.tv/interface/contentv3/' + real_id, real_id, 'Downloading video info')
- info = json.loads(info)
+ info = self._download_json('http://www.wat.tv/interface/contentv3/' + real_id, real_id)
return info['media']
-
def _real_extract(self, url):
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)
+
+ geo_list = video_info.get('geoList')
+ country = geo_list[0] if geo_list else ''
+
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')
entries = [self.url_result(chapter_url) for chapter_url in chapter_urls]
return self.playlist_result(entries, real_id, video_info['title'])
+ upload_date = None
+ if 'date_diffusion' in first_chapter:
+ 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
- info = {'id': real_id,
- 'url': 'http://wat.tv/get/android5/%s.mp4' % real_id,
+
+ 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(self._download_webpage(
+ 'http://www.wat.tv/servertime', real_id,
+ 'Downloading server time').split('|')[0])
+ 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&country=%s' % (webid, compute_token(webid), country),
+ 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',
- 'title': first_chapter['title'],
- 'thumbnail': first_chapter['preview'],
- 'description': first_chapter['description'],
- 'view_count': video_info['views'],
- }
- if 'date_diffusion' in first_chapter:
- info['upload_date'] = unified_strdate(first_chapter['date_diffusion'])
+ 'format_id': fmt[0],
+ })
- return info
+ return {
+ 'id': 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,
+ }
projects / youtube-dl / blobdiff