aboutsummaryrefslogtreecommitdiffstats
path: root/youtube_dl/extractor/viewster.py
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/extractor/viewster.py')
-rw-r--r--youtube_dl/extractor/viewster.py95
1 files changed, 72 insertions, 23 deletions
diff --git a/youtube_dl/extractor/viewster.py b/youtube_dl/extractor/viewster.py
index 393b63618..7839225d4 100644
--- a/youtube_dl/extractor/viewster.py
+++ b/youtube_dl/extractor/viewster.py
@@ -1,27 +1,34 @@
# coding: utf-8
from __future__ import unicode_literals
+import re
+
from .common import InfoExtractor
from ..compat import (
- compat_urllib_request,
+ compat_HTTPError,
compat_urllib_parse,
+ compat_urllib_parse_unquote,
)
from ..utils import (
determine_ext,
+ ExtractorError,
int_or_none,
parse_iso8601,
+ sanitized_Request,
+ HEADRequest,
+ url_basename,
)
class ViewsterIE(InfoExtractor):
- _VALID_URL = r'http://(?:www\.)?viewster\.com/(?:serie|movie)/(?P<id>\d+-\d+-\d+)'
+ _VALID_URL = r'https?://(?:www\.)?viewster\.com/(?:serie|movie)/(?P<id>\d+-\d+-\d+)'
_TESTS = [{
# movie, Type=Movie
'url': 'http://www.viewster.com/movie/1140-11855-000/the-listening-project/',
- 'md5': '14d3cfffe66d57b41ae2d9c873416f01',
+ 'md5': 'e642d1b27fcf3a4ffa79f194f5adde36',
'info_dict': {
'id': '1140-11855-000',
- 'ext': 'flv',
+ 'ext': 'mp4',
'title': 'The listening Project',
'description': 'md5:bac720244afd1a8ea279864e67baa071',
'timestamp': 1214870400,
@@ -31,10 +38,10 @@ class ViewsterIE(InfoExtractor):
}, {
# series episode, Type=Episode
'url': 'http://www.viewster.com/serie/1284-19427-001/the-world-and-a-wall/',
- 'md5': 'd5434c80fcfdb61651cc2199a88d6ba3',
+ 'md5': '9243079a8531809efe1b089db102c069',
'info_dict': {
'id': '1284-19427-001',
- 'ext': 'flv',
+ 'ext': 'mp4',
'title': 'The World and a Wall',
'description': 'md5:24814cf74d3453fdf5bfef9716d073e3',
'timestamp': 1428192000,
@@ -59,12 +66,20 @@ class ViewsterIE(InfoExtractor):
'description': 'md5:e7097a8fc97151e25f085c9eb7a1cdb1',
},
'playlist_mincount': 16,
+ }, {
+ # geo restricted series
+ 'url': 'https://www.viewster.com/serie/1280-18794-002/',
+ 'only_matching': True,
+ }, {
+ # geo restricted video
+ 'url': 'https://www.viewster.com/serie/1280-18794-002/what-is-extraterritoriality-lawo/',
+ 'only_matching': True,
}]
_ACCEPT_HEADER = 'application/json, text/javascript, */*; q=0.01'
def _download_json(self, url, video_id, note='Downloading JSON metadata', fatal=True):
- request = compat_urllib_request.Request(url)
+ request = sanitized_Request(url)
request.add_header('Accept', self._ACCEPT_HEADER)
request.add_header('Auth-token', self._AUTH_TOKEN)
return super(ViewsterIE, self)._download_json(request, video_id, note, fatal=fatal)
@@ -72,9 +87,9 @@ class ViewsterIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
# Get 'api_token' cookie
- self._request_webpage(url, video_id)
- cookies = self._get_cookies(url)
- self._AUTH_TOKEN = compat_urllib_parse.unquote(cookies['api_token'].value)
+ self._request_webpage(HEADRequest('http://www.viewster.com/'), video_id)
+ cookies = self._get_cookies('http://www.viewster.com/')
+ self._AUTH_TOKEN = compat_urllib_parse_unquote(cookies['api_token'].value)
info = self._download_json(
'https://public-api.viewster.com/search/%s' % video_id,
@@ -83,10 +98,16 @@ class ViewsterIE(InfoExtractor):
entry_id = info.get('Id') or info['id']
# unfinished serie has no Type
- if info.get('Type') in ['Serie', None]:
- episodes = self._download_json(
- 'https://public-api.viewster.com/series/%s/episodes' % entry_id,
- video_id, 'Downloading series JSON')
+ if info.get('Type') in ('Serie', None):
+ try:
+ episodes = self._download_json(
+ 'https://public-api.viewster.com/series/%s/episodes' % entry_id,
+ video_id, 'Downloading series JSON')
+ except ExtractorError as e:
+ if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
+ self.raise_geo_restricted()
+ else:
+ raise
entries = [
self.url_result(
'http://www.viewster.com/movie/%s' % episode['OriginId'], 'Viewster')
@@ -96,7 +117,8 @@ class ViewsterIE(InfoExtractor):
return self.playlist_result(entries, video_id, title, description)
formats = []
- for media_type in ('application/f4m+xml', 'application/x-mpegURL'):
+ manifest_url = None
+ for media_type in ('application/f4m+xml', 'application/x-mpegURL', 'video/mp4'):
media = self._download_json(
'https://public-api.viewster.com/movies/%s/video?mediaType=%s'
% (entry_id, compat_urllib_parse.quote(media_type)),
@@ -108,25 +130,52 @@ class ViewsterIE(InfoExtractor):
continue
ext = determine_ext(video_url)
if ext == 'f4m':
+ manifest_url = video_url
video_url += '&' if '?' in video_url else '?'
video_url += 'hdcore=3.2.0&plugin=flowplayer-3.2.0.1'
formats.extend(self._extract_f4m_formats(
video_url, video_id, f4m_id='hds'))
elif ext == 'm3u8':
- formats.extend(self._extract_m3u8_formats(
+ manifest_url = video_url
+ m3u8_formats = self._extract_m3u8_formats(
video_url, video_id, 'mp4', m3u8_id='hls',
- fatal=False # m3u8 sometimes fail
- ))
+ fatal=False) # m3u8 sometimes fail
+ if m3u8_formats:
+ formats.extend(m3u8_formats)
else:
- formats.append({
- 'url': video_url,
- })
+ qualities_basename = self._search_regex(
+ '/([^/]+)\.csmil/',
+ manifest_url, 'qualities basename', default=None)
+ if not qualities_basename:
+ continue
+ QUALITIES_RE = r'((,\d+k)+,?)'
+ qualities = self._search_regex(
+ QUALITIES_RE, qualities_basename,
+ 'qualities', default=None)
+ if not qualities:
+ continue
+ qualities = qualities.strip(',').split(',')
+ http_template = re.sub(QUALITIES_RE, r'%s', qualities_basename)
+ http_url_basename = url_basename(video_url)
+ for q in qualities:
+ tbr = int_or_none(self._search_regex(
+ r'(\d+)k', q, 'bitrate', default=None))
+ formats.append({
+ 'url': video_url.replace(http_url_basename, http_template % q),
+ 'ext': 'mp4',
+ 'format_id': 'http' + ('-%d' % tbr if tbr else ''),
+ 'tbr': tbr,
+ })
+
+ if not formats and not info.get('LanguageSets') and not info.get('VODSettings'):
+ self.raise_geo_restricted()
+
self._sort_formats(formats)
- synopsis = info.get('Synopsis', {})
+ synopsis = info.get('Synopsis') or {}
# Prefer title outside synopsis since it's less messy
title = (info.get('Title') or synopsis['Title']).strip()
- description = synopsis.get('Detailed') or info.get('Synopsis', {}).get('Short')
+ description = synopsis.get('Detailed') or (info.get('Synopsis') or {}).get('Short')
duration = int_or_none(info.get('Duration'))
timestamp = parse_iso8601(info.get('ReleaseDate'))
generated by cgit v1.2.3 (git 2.25.1) at 2025-07-25 00:14:45 +0000