Merge remote-tracking branch 'origin/master'

This commit is contained in:
Philipp Hagemeister 2014-08-24 01:34:28 +02:00
commit 30b871b0ca

View File

@ -2,27 +2,30 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re import re
import time
import hashlib
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
ExtractorError,
unified_strdate, unified_strdate,
) )
class WatIE(InfoExtractor): 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' IE_NAME = 'wat.tv'
_TEST = { _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': { 'info_dict': {
'id': '10631273', 'id': '11713067',
'display_id': 'soupe-figues-l-orange-aux-epices',
'ext': 'mp4', 'ext': 'mp4',
'title': 'World War Z - Philadelphia VOST', 'title': 'Soupe de figues à l\'orange et aux épices',
'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', 'description': 'Retrouvez l\'émission "Petits plats en équilibre", diffusée le 18 août 2014.',
}, 'upload_date': '20140819',
'params': { 'duration': 120,
# Sometimes wat serves the whole file with the --test option
'skip_download': True,
}, },
} }
@ -36,13 +39,20 @@ def _real_extract(self, url):
def real_id_for_chapter(chapter): def real_id_for_chapter(chapter):
return chapter['tc_start'].split('-')[0] return chapter['tc_start'].split('-')[0]
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
short_id = mobj.group('shortID') short_id = mobj.group('short_id')
webpage = self._download_webpage(url, 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') real_id = self._search_regex(r'xtpage = ".*-(.*?)";', webpage, 'real id')
video_info = self.download_video_info(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'] chapters = video_info['chapters']
first_chapter = chapters[0] first_chapter = chapters[0]
files = video_info['files']
first_file = files[0]
if real_id_for_chapter(first_chapter) != real_id: if real_id_for_chapter(first_chapter) != real_id:
self.to_screen('Multipart video detected') self.to_screen('Multipart video detected')
@ -61,12 +71,45 @@ def real_id_for_chapter(chapter):
upload_date = unified_strdate(first_chapter['date_diffusion']) upload_date = unified_strdate(first_chapter['date_diffusion'])
# Otherwise we can continue and extract just one part, we have to use # Otherwise we can continue and extract just one part, we have to use
# the short id for getting the video url # 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 { return {
'id': real_id, 'id': real_id,
'url': 'http://wat.tv/get/android5/%s.mp4' % real_id, 'display_id': display_id,
'title': first_chapter['title'], 'title': first_chapter['title'],
'thumbnail': first_chapter['preview'], 'thumbnail': first_chapter['preview'],
'description': first_chapter['description'], 'description': first_chapter['description'],
'view_count': video_info['views'], 'view_count': video_info['views'],
'upload_date': upload_date, 'upload_date': upload_date,
'duration': first_file['duration'],
'formats': formats,
} }