aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/wat.py
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/extractor/wat.py')
-rw-r--r--youtube_dl/extractor/wat.py155
1 files changed, 62 insertions, 93 deletions
diff --git a/youtube_dl/extractor/wat.py b/youtube_dl/extractor/wat.py
index affcc52f6..b15e03768 100644
--- a/youtube_dl/extractor/wat.py
+++ b/youtube_dl/extractor/wat.py
@@ -1,137 +1,106 @@
# coding: utf-8
from __future__ import unicode_literals
-import re
-import hashlib
-
from .common import InfoExtractor
+from ..compat import compat_str
from ..utils import (
ExtractorError,
+ int_or_none,
+ try_get,
unified_strdate,
)
class WatIE(InfoExtractor):
- _VALID_URL = r'http://www\.wat\.tv/video/(?P<display_id>.*)-(?P<short_id>.*?)_.*?\.html'
+ _VALID_URL = r'(?:wat:|https?://(?:www\.)?wat\.tv/video/.*-)(?P<id>[0-9a-z]+)'
IE_NAME = 'wat.tv'
_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,
},
+ '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',
- 'md5': 'fbc84e4378165278e743956d9c1bf16b',
+ 'md5': 'b16574df2c3cd1a36ca0098f2a791925',
'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,
},
- 'skip': "Ce contenu n'est pas disponible pour l'instant.",
+ 'expected_warnings': ["Ce contenu n'est pas disponible pour l'instant."],
+ 'skip': 'This content is no longer available',
},
]
-
- 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_json('http://www.wat.tv/interface/contentv3/' + real_id, real_id)
- return info['media']
+ _GEO_BYPASS = False
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('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_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))
- video_info = self.download_video_info(real_id)
+ # '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']
error_desc = video_info.get('error_desc')
if error_desc:
- raise ExtractorError(
- '%s returned error: %s' % (self.IE_NAME, error_desc), expected=True)
-
- 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')
- chapter_urls = []
- for chapter in chapters:
- chapter_id = real_id_for_chapter(chapter)
- # Yes, when we this chapter is processed by WatIE,
- # it will download the info again
- chapter_info = self.download_video_info(chapter_id)
- chapter_urls.append(chapter_info['url'])
- 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
-
- 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,
- 'Downloading %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],
- })
+ if video_info.get('error_code') == 'GEOBLOCKED':
+ self.raise_geo_restricted(error_desc, video_info.get('geoList'))
+ raise ExtractorError(error_desc, expected=True)
+
+ title = video_info['title']
+
+ formats = []
+
+ 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))
+
+ 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)
+
+ self._sort_formats(formats)
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'],
+ '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,
}
generated by cgit v1.2.3 (git 2.26.2) at 2025-11-09 05:58:04 +0000