1
0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-30 16:33:14 +01:00
youtube-dl/youtube_dl/extractor/wat.py

107 lines
4.0 KiB
Python
Raw Normal View History

# coding: utf-8
2014-03-29 15:15:16 +01:00
from __future__ import unicode_literals
2013-06-28 22:01:47 +02:00
from .common import InfoExtractor
2016-04-22 10:36:14 +02:00
from ..compat import compat_str
2014-09-23 14:58:35 +02:00
from ..utils import (
ExtractorError,
int_or_none,
try_get,
unified_strdate,
2014-09-23 14:58:35 +02:00
)
2013-06-28 22:01:47 +02:00
class WatIE(InfoExtractor):
2016-04-22 10:36:14 +02:00
_VALID_URL = r'(?:wat:|https?://(?:www\.)?wat\.tv/video/.*-)(?P<id>[0-9a-z]+)'
2013-06-28 22:01:47 +02:00
IE_NAME = 'wat.tv'
_TESTS = [
{
'url': 'http://www.wat.tv/video/soupe-figues-l-orange-aux-epices-6z1uz_2hvf7_.html',
'info_dict': {
'id': '11713067',
'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,
},
2018-06-17 16:56:52 +02:00
'params': {
# m3u8 download
'skip_download': True,
},
'expected_warnings': ['HTTP Error 404'],
'skip': 'This content is no longer available',
},
{
'url': 'http://www.wat.tv/video/gregory-lemarchal-voix-ange-6z1v7_6ygkj_.html',
2018-06-17 16:56:52 +02:00
'md5': 'b16574df2c3cd1a36ca0098f2a791925',
'info_dict': {
'id': '11713075',
'ext': 'mp4',
'title': 'Grégory Lemarchal, une voix d\'ange depuis 10 ans (1/3)',
'upload_date': '20140816',
},
'expected_warnings': ["Ce contenu n'est pas disponible pour l'instant."],
'skip': 'This content is no longer available',
},
]
_GEO_BYPASS = False
2014-03-29 15:15:16 +01:00
2013-06-28 22:01:47 +02:00
def _real_extract(self, url):
2016-04-22 10:36:14 +02:00
video_id = self._match_id(url)
video_id = video_id if video_id.isdigit() and len(video_id) > 6 else compat_str(int(video_id, 36))
2016-04-22 10:36:14 +02:00
# 'contentv4' is used in the website, but it also returns the related
# videos, we don't need them
# video_data = self._download_json(
# 'http://www.wat.tv/interface/contentv4s/' + video_id, video_id)
video_data = self._download_json(
'https://mediainfo.tf1.fr/mediainfocombo/' + video_id,
video_id, query={'context': 'MYTF1', 'pver': '4001000'})
video_info = video_data['media']
2014-09-23 14:58:35 +02:00
error_desc = video_info.get('error_desc')
if error_desc:
if video_info.get('error_code') == 'GEOBLOCKED':
self.raise_geo_restricted(error_desc, video_info.get('geoList'))
raise ExtractorError(error_desc, expected=True)
2013-06-28 22:01:47 +02:00
title = video_info['title']
formats = []
2016-04-22 10:36:14 +02:00
def extract_formats(manifest_urls):
for f, f_url in manifest_urls.items():
if not f_url:
continue
if f in ('dash', 'mpd'):
formats.extend(self._extract_mpd_formats(
f_url.replace('://das-q1.tf1.fr/', '://das-q1-ssl.tf1.fr/'),
video_id, mpd_id='dash', fatal=False))
elif f == 'hls':
formats.extend(self._extract_m3u8_formats(
f_url, video_id, 'mp4',
'm3u8_native', m3u8_id='hls', fatal=False))
2016-04-22 10:36:14 +02:00
delivery = video_data.get('delivery') or {}
extract_formats({delivery.get('format'): delivery.get('url')})
if not formats:
if delivery.get('drm'):
raise ExtractorError('This video is DRM protected.', expected=True)
manifest_urls = self._download_json(
'http://www.wat.tv/get/webhtml/' + video_id, video_id, fatal=False)
if manifest_urls:
extract_formats(manifest_urls)
2016-09-06 21:44:45 +02:00
self._sort_formats(formats)
2014-03-29 15:15:16 +01:00
return {
2016-04-22 10:36:14 +02:00
'id': video_id,
'title': title,
'thumbnail': video_info.get('preview'),
'upload_date': unified_strdate(try_get(
video_data, lambda x: x['mediametrie']['chapters'][0]['estatS4'])),
'duration': int_or_none(video_info.get('duration')),
'formats': formats,
2014-03-29 15:15:16 +01:00
}