# coding: utf-8
from __future__ import unicode_literals
+import json
import re
from .common import InfoExtractor
ExtractorError,
float_or_none,
int_or_none,
+ strip_or_none,
unified_timestamp,
)
class DPlayIE(InfoExtractor):
+ _PATH_REGEX = r'/(?P<id>[^/]+/[^/?#]+)'
_VALID_URL = r'''(?x)https?://
(?P<domain>
(?:www\.)?(?P<host>d
)
)|
(?P<subdomain_country>es|it)\.dplay\.com
- )/[^/]+/(?P<id>[^/]+/[^/?#]+)'''
+ )/[^/]+''' + _PATH_REGEX
_TESTS = [{
# non geo restricted, via secure api, unsigned download hls URL
'only_matching': True,
}]
+ def _process_errors(self, e, geo_countries):
+ info = self._parse_json(e.cause.read().decode('utf-8'), None)
+ error = info['errors'][0]
+ error_code = error.get('code')
+ if error_code == 'access.denied.geoblocked':
+ self.raise_geo_restricted(countries=geo_countries)
+ elif error_code in ('access.denied.missingpackage', 'invalid.token'):
+ raise ExtractorError(
+ 'This video is only available for registered users. You may want to use --cookies.', expected=True)
+ raise ExtractorError(info['errors'][0]['detail'], expected=True)
+
+ def _update_disco_api_headers(self, headers, disco_base, display_id, realm):
+ headers['Authorization'] = 'Bearer ' + self._download_json(
+ disco_base + 'token', display_id, 'Downloading token',
+ query={
+ 'realm': realm,
+ })['data']['attributes']['token']
+
+ def _download_video_playback_info(self, disco_base, video_id, headers):
+ streaming = self._download_json(
+ disco_base + 'playback/videoPlaybackInfo/' + video_id,
+ video_id, headers=headers)['data']['attributes']['streaming']
+ streaming_list = []
+ for format_id, format_dict in streaming.items():
+ streaming_list.append({
+ 'type': format_id,
+ 'url': format_dict.get('url'),
+ })
+ return streaming_list
+
def _get_disco_api_info(self, url, display_id, disco_host, realm, country):
geo_countries = [country.upper()]
self._initialize_geo_bypass({
'countries': geo_countries,
})
disco_base = 'https://%s/' % disco_host
- token = self._download_json(
- disco_base + 'token', display_id, 'Downloading token',
- query={
- 'realm': realm,
- })['data']['attributes']['token']
headers = {
'Referer': url,
- 'Authorization': 'Bearer ' + token,
}
- video = self._download_json(
- disco_base + 'content/videos/' + display_id, display_id,
- headers=headers, query={
- 'fields[channel]': 'name',
- 'fields[image]': 'height,src,width',
- 'fields[show]': 'name',
- 'fields[tag]': 'name',
- 'fields[video]': 'description,episodeNumber,name,publishStart,seasonNumber,videoDuration',
- 'include': 'images,primaryChannel,show,tags'
- })
+ self._update_disco_api_headers(headers, disco_base, display_id, realm)
+ try:
+ video = self._download_json(
+ disco_base + 'content/videos/' + display_id, display_id,
+ headers=headers, query={
+ 'fields[channel]': 'name',
+ 'fields[image]': 'height,src,width',
+ 'fields[show]': 'name',
+ 'fields[tag]': 'name',
+ 'fields[video]': 'description,episodeNumber,name,publishStart,seasonNumber,videoDuration',
+ 'include': 'images,primaryChannel,show,tags'
+ })
+ except ExtractorError as e:
+ if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400:
+ self._process_errors(e, geo_countries)
+ raise
video_id = video['data']['id']
info = video['data']['attributes']
title = info['name'].strip()
formats = []
try:
- streaming = self._download_json(
- disco_base + 'playback/videoPlaybackInfo/' + video_id,
- display_id, headers=headers)['data']['attributes']['streaming']
+ streaming = self._download_video_playback_info(
+ disco_base, video_id, headers)
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
- info = self._parse_json(e.cause.read().decode('utf-8'), display_id)
- error = info['errors'][0]
- error_code = error.get('code')
- if error_code == 'access.denied.geoblocked':
- self.raise_geo_restricted(countries=geo_countries)
- elif error_code == 'access.denied.missingpackage':
- self.raise_login_required()
- raise ExtractorError(info['errors'][0]['detail'], expected=True)
+ self._process_errors(e, geo_countries)
raise
- for format_id, format_dict in streaming.items():
+ for format_dict in streaming:
if not isinstance(format_dict, dict):
continue
format_url = format_dict.get('url')
if not format_url:
continue
+ format_id = format_dict.get('type')
ext = determine_ext(format_url)
if format_id == 'dash' or ext == 'mpd':
formats.extend(self._extract_mpd_formats(
'id': video_id,
'display_id': display_id,
'title': title,
- 'description': info.get('description'),
+ 'description': strip_or_none(info.get('description')),
'duration': float_or_none(info.get('videoDuration'), 1000),
'timestamp': unified_timestamp(info.get('publishStart')),
'series': series,
host = 'disco-api.' + domain if domain[0] == 'd' else 'eu2-prod.disco-api.com'
return self._get_disco_api_info(
url, display_id, host, 'dplay' + country, country)
+
+
+class DiscoveryPlusIE(DPlayIE):
+ _VALID_URL = r'https?://(?:www\.)?discoveryplus\.com/video' + DPlayIE._PATH_REGEX
+ _TESTS = [{
+ 'url': 'https://www.discoveryplus.com/video/property-brothers-forever-home/food-and-family',
+ 'info_dict': {
+ 'id': '1140794',
+ 'display_id': 'property-brothers-forever-home/food-and-family',
+ 'ext': 'mp4',
+ 'title': 'Food and Family',
+ 'description': 'The brothers help a Richmond family expand their single-level home.',
+ 'duration': 2583.113,
+ 'timestamp': 1609304400,
+ 'upload_date': '20201230',
+ 'creator': 'HGTV',
+ 'series': 'Property Brothers: Forever Home',
+ 'season_number': 1,
+ 'episode_number': 1,
+ },
+ 'skip': 'Available for Premium users',
+ }]
+
+ def _update_disco_api_headers(self, headers, disco_base, display_id, realm):
+ headers['x-disco-client'] = 'WEB:UNKNOWN:dplus_us:15.0.0'
+
+ def _download_video_playback_info(self, disco_base, video_id, headers):
+ return self._download_json(
+ disco_base + 'playback/v3/videoPlaybackInfo',
+ video_id, headers=headers, data=json.dumps({
+ 'deviceInfo': {
+ 'adBlocker': False,
+ },
+ 'videoId': video_id,
+ 'wisteriaProperties': {
+ 'platform': 'desktop',
+ },
+ }).encode('utf-8'))['data']['attributes']['streaming']
+
+ def _real_extract(self, url):
+ display_id = self._match_id(url)
+ return self._get_disco_api_info(
+ url, display_id, 'us1-prod-direct.discoveryplus.com', 'go', 'us')
+
+
+class HGTVDeIE(DPlayIE):
+ _VALID_URL = r'https?://de\.hgtv\.com/sendungen' + DPlayIE._PATH_REGEX
+ _TESTS = [{
+ 'url': 'https://de.hgtv.com/sendungen/tiny-house-klein-aber-oho/wer-braucht-schon-eine-toilette/',
+ 'info_dict': {
+ 'id': '151205',
+ 'display_id': 'tiny-house-klein-aber-oho/wer-braucht-schon-eine-toilette',
+ 'ext': 'mp4',
+ 'title': 'Wer braucht schon eine Toilette',
+ 'description': 'md5:05b40a27e7aed2c9172de34d459134e2',
+ 'duration': 1177.024,
+ 'timestamp': 1595705400,
+ 'upload_date': '20200725',
+ 'creator': 'HGTV',
+ 'series': 'Tiny House - klein, aber oho',
+ 'season_number': 3,
+ 'episode_number': 3,
+ },
+ 'params': {
+ 'format': 'bestvideo',
+ },
+ }]
+
+ def _real_extract(self, url):
+ display_id = self._match_id(url)
+ return self._get_disco_api_info(
+ url, display_id, 'eu1-prod.disco-api.com', 'hgtv', 'de')
projects / yt-dlp.git / blobdiff