From 0cf2352e858982ed811122cf867fb5e25694d97a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 8 Mar 2017 21:19:08 +0700 Subject: [dplayit] Separate and rewrite extractor and bypass geo restriction (closes #12393) --- youtube_dl/extractor/dplay.py | 117 ++++++++++++++++++++++++++++++++++-------- 1 file changed, 96 insertions(+), 21 deletions(-) (limited to 'youtube_dl/extractor/dplay.py') diff --git a/youtube_dl/extractor/dplay.py b/youtube_dl/extractor/dplay.py index 32028bc3b..62e676389 100644 --- a/youtube_dl/extractor/dplay.py +++ b/youtube_dl/extractor/dplay.py @@ -6,37 +6,24 @@ import re import time from .common import InfoExtractor -from ..compat import compat_urlparse +from ..compat import ( + compat_urlparse, + compat_HTTPError, +) from ..utils import ( USER_AGENTS, + ExtractorError, int_or_none, + unified_strdate, + remove_end, update_url_query, ) class DPlayIE(InfoExtractor): - _VALID_URL = r'https?://(?Pit\.dplay\.com|www\.dplay\.(?:dk|se|no))/[^/]+/(?P[^/?#]+)' + _VALID_URL = r'https?://(?Pwww\.dplay\.(?:dk|se|no))/[^/]+/(?P[^/?#]+)' _TESTS = [{ - # geo restricted, via direct unsigned hls URL - 'url': 'http://it.dplay.com/take-me-out/stagione-1-episodio-25/', - 'info_dict': { - 'id': '1255600', - 'display_id': 'stagione-1-episodio-25', - 'ext': 'mp4', - 'title': 'Episodio 25', - 'description': 'md5:cae5f40ad988811b197d2d27a53227eb', - 'duration': 2761, - 'timestamp': 1454701800, - 'upload_date': '20160205', - 'creator': 'RTIT', - 'series': 'Take me out', - 'season_number': 1, - 'episode_number': 25, - 'age_limit': 0, - }, - 'expected_warnings': ['Unable to download f4m manifest'], - }, { # non geo restricted, via secure api, unsigned download hls URL 'url': 'http://www.dplay.se/nugammalt-77-handelser-som-format-sverige/season-1-svensken-lar-sig-njuta-av-livet/', 'info_dict': { @@ -168,3 +155,91 @@ class DPlayIE(InfoExtractor): 'formats': formats, 'subtitles': subtitles, } + + +class DPlayItIE(InfoExtractor): + _VALID_URL = r'https?://it\.dplay\.com/[^/]+/[^/]+/(?P[^/?#]+)' + _GEO_COUNTRIES = ['IT'] + _TEST = { + 'url': 'http://it.dplay.com/nove/biografie-imbarazzanti/luigi-di-maio-la-psicosi-di-stanislawskij/', + 'md5': '2b808ffb00fc47b884a172ca5d13053c', + 'info_dict': { + 'id': '6918', + 'display_id': 'luigi-di-maio-la-psicosi-di-stanislawskij', + 'ext': 'mp4', + 'title': 'Biografie imbarazzanti: Luigi Di Maio: la psicosi di Stanislawskij', + 'description': 'md5:3c7a4303aef85868f867a26f5cc14813', + 'thumbnail': r're:^https?://.*\.jpe?g', + 'upload_date': '20160524', + 'series': 'Biografie imbarazzanti', + 'season_number': 1, + 'episode': 'Luigi Di Maio: la psicosi di Stanislawskij', + 'episode_number': 1, + }, + } + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + video_id = self._search_regex( + r'url\s*:\s*["\']https://dplay-south-prod\.disco-api\.com/playback/videoPlaybackInfo/(\d+)', + webpage, 'video id') + + title = remove_end(self._og_search_title(webpage), ' | Dplay') + + try: + info = self._download_json( + 'https://dplay-south-prod.disco-api.com/playback/videoPlaybackInfo/%s' % video_id, + display_id, headers={ + 'Authorization': 'Bearer %s' % self._get_cookies(url).get( + 'dplayit_token').value, + 'Referer': url, + }) + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code in (400, 403): + info = self._parse_json(e.cause.read().decode('utf-8'), display_id) + error = info['errors'][0] + if error.get('code') == 'access.denied.geoblocked': + self.raise_geo_restricted( + msg=error.get('detail'), countries=self._GEO_COUNTRIES) + raise ExtractorError(info['errors'][0]['detail'], expected=True) + raise + + hls_url = info['data']['attributes']['streaming']['hls']['url'] + + formats = self._extract_m3u8_formats( + hls_url, display_id, ext='mp4', entry_protocol='m3u8_native', + m3u8_id='hls') + + series = self._html_search_regex( + r'(?s)]+class=["\'].*?\bshow_title\b.*?["\'][^>]*>(.+?)', + webpage, 'series', fatal=False) + episode = self._search_regex( + r']+class=["\'].*?\bdesc_ep\b.*?["\'][^>]*>\s*
\s*([^<]+)', + webpage, 'episode', fatal=False) + + mobj = re.search( + r'(?s)]+class=["\']dates["\'][^>]*>.+?\bS\.(?P\d+)\s+E\.(?P\d+)\s*-\s*(?P\d{2}/\d{2}/\d{4})', + webpage) + if mobj: + season_number = int(mobj.group('season_number')) + episode_number = int(mobj.group('episode_number')) + upload_date = unified_strdate(mobj.group('upload_date')) + else: + season_number = episode_number = upload_date = None + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': self._og_search_description(webpage), + 'thumbnail': self._og_search_thumbnail(webpage), + 'series': series, + 'season_number': season_number, + 'episode': episode, + 'episode_number': episode_number, + 'upload_date': upload_date, + 'formats': formats, + } -- cgit v1.2.3 From 0e7f9a9b48700efd40c4068b00364a7963dc9265 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 8 Mar 2017 21:30:30 +0700 Subject: [dplayit] Relax playback info URL extraction --- youtube_dl/extractor/dplay.py | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'youtube_dl/extractor/dplay.py') diff --git a/youtube_dl/extractor/dplay.py b/youtube_dl/extractor/dplay.py index 62e676389..87c5dd63e 100644 --- a/youtube_dl/extractor/dplay.py +++ b/youtube_dl/extractor/dplay.py @@ -183,16 +183,15 @@ class DPlayItIE(InfoExtractor): webpage = self._download_webpage(url, display_id) - video_id = self._search_regex( - r'url\s*:\s*["\']https://dplay-south-prod\.disco-api\.com/playback/videoPlaybackInfo/(\d+)', + info_url = self._search_regex( + r'url\s*:\s*["\']((?:https?:)?//[^/]+/playback/videoPlaybackInfo/\d+)', webpage, 'video id') title = remove_end(self._og_search_title(webpage), ' | Dplay') try: info = self._download_json( - 'https://dplay-south-prod.disco-api.com/playback/videoPlaybackInfo/%s' % video_id, - display_id, headers={ + info_url, display_id, headers={ 'Authorization': 'Bearer %s' % self._get_cookies(url).get( 'dplayit_token').value, 'Referer': url, @@ -231,7 +230,7 @@ class DPlayItIE(InfoExtractor): season_number = episode_number = upload_date = None return { - 'id': video_id, + 'id': info_url.rpartition('/')[-1], 'display_id': display_id, 'title': title, 'description': self._og_search_description(webpage), -- cgit v1.2.3