From 80f48920c8a909ba55d13932524e55ed970f1c6a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 18 Oct 2015 06:57:57 +0600 Subject: [crunchyroll] Bypass maturity wall (Closes #7202) --- youtube_dl/extractor/crunchyroll.py | 59 ++++++++++++++++++++++--------------- 1 file changed, 36 insertions(+), 23 deletions(-) (limited to 'youtube_dl/extractor/crunchyroll.py') diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index 95952bc29..aa258bbc2 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -32,6 +32,26 @@ from ..aes import ( class CrunchyrollBaseIE(InfoExtractor): + _NETRC_MACHINE = 'crunchyroll' + + def _login(self): + (username, password) = self._get_login_info() + if username is None: + return + self.report_login() + login_url = 'https://www.crunchyroll.com/?a=formhandler' + data = urlencode_postdata({ + 'formname': 'RpcApiUser_Login', + 'name': username, + 'password': password, + }) + login_request = compat_urllib_request.Request(login_url, data) + login_request.add_header('Content-Type', 'application/x-www-form-urlencoded') + self._download_webpage(login_request, None, False, 'Wrong login info') + + def _real_initialize(self): + self._login() + def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5, encoding=None): request = (url_or_request if isinstance(url_or_request, compat_urllib_request.Request) else compat_urllib_request.Request(url_or_request)) @@ -46,10 +66,22 @@ class CrunchyrollBaseIE(InfoExtractor): return super(CrunchyrollBaseIE, self)._download_webpage( request, video_id, note, errnote, fatal, tries, timeout, encoding) + @staticmethod + def _add_skip_wall(url): + parsed_url = compat_urlparse.urlparse(url) + qs = compat_urlparse.parse_qs(parsed_url.query) + # Always force skip_wall to bypass maturity wall, namely 18+ confirmation message: + # > This content may be inappropriate for some people. + # > Are you sure you want to continue? + # since it's not disabled by default in crunchyroll account's settings. + # See https://github.com/rg3/youtube-dl/issues/7202. + qs['skip_wall'] = ['1'] + return compat_urlparse.urlunparse( + parsed_url._replace(query=compat_urllib_parse.urlencode(qs, True))) + class CrunchyrollIE(CrunchyrollBaseIE): _VALID_URL = r'https?://(?:(?Pwww|m)\.)?(?Pcrunchyroll\.(?:com|fr)/(?:media(?:-|/\?id=)|[^/]*/[^/?&]*?)(?P[0-9]+))(?:[/?&]|$)' - _NETRC_MACHINE = 'crunchyroll' _TESTS = [{ 'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513', 'info_dict': { @@ -81,7 +113,6 @@ class CrunchyrollIE(CrunchyrollBaseIE): # rtmp 'skip_download': True, }, - }, { 'url': 'http://www.crunchyroll.fr/girl-friend-beta/episode-11-goodbye-la-mode-661697', 'only_matching': True, @@ -94,24 +125,6 @@ class CrunchyrollIE(CrunchyrollBaseIE): '1080': ('80', '108'), } - def _login(self): - (username, password) = self._get_login_info() - if username is None: - return - self.report_login() - login_url = 'https://www.crunchyroll.com/?a=formhandler' - data = urlencode_postdata({ - 'formname': 'RpcApiUser_Login', - 'name': username, - 'password': password, - }) - login_request = compat_urllib_request.Request(login_url, data) - login_request.add_header('Content-Type', 'application/x-www-form-urlencoded') - self._download_webpage(login_request, None, False, 'Wrong login info') - - def _real_initialize(self): - self._login() - def _decrypt_subtitles(self, data, iv, id): data = bytes_to_intlist(base64.b64decode(data.encode('utf-8'))) iv = bytes_to_intlist(base64.b64decode(iv.encode('utf-8'))) @@ -254,7 +267,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text else: webpage_url = 'http://www.' + mobj.group('url') - webpage = self._download_webpage(webpage_url, video_id, 'Downloading webpage') + webpage = self._download_webpage(self._add_skip_wall(webpage_url), video_id, 'Downloading webpage') note_m = self._html_search_regex( r'
(.+?)
', webpage, 'trailer-notice', default='') @@ -352,7 +365,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text class CrunchyrollShowPlaylistIE(CrunchyrollBaseIE): IE_NAME = "crunchyroll:playlist" - _VALID_URL = r'https?://(?:(?Pwww|m)\.)?(?Pcrunchyroll\.com/(?!(?:news|anime-news|library|forum|launchcalendar|lineup|store|comics|freetrial|login))(?P[\w\-]+))/?$' + _VALID_URL = r'https?://(?:(?Pwww|m)\.)?(?Pcrunchyroll\.com/(?!(?:news|anime-news|library|forum|launchcalendar|lineup|store|comics|freetrial|login))(?P[\w\-]+))/?(?:\?|$)' _TESTS = [{ 'url': 'http://www.crunchyroll.com/a-bridge-to-the-starry-skies-hoshizora-e-kakaru-hashi', @@ -366,7 +379,7 @@ class CrunchyrollShowPlaylistIE(CrunchyrollBaseIE): def _real_extract(self, url): show_id = self._match_id(url) - webpage = self._download_webpage(url, show_id) + webpage = self._download_webpage(self._add_skip_wall(url), show_id) title = self._html_search_regex( r'(?s)]*>\s*(.*?)', webpage, 'title') -- cgit v1.2.3 From 49941c4e4f6e33785a3be1e0d103bd81657d8a0d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 18 Oct 2015 07:06:47 +0600 Subject: [crunchyroll] Add maturity wall reference tests (#7202) --- youtube_dl/extractor/crunchyroll.py | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'youtube_dl/extractor/crunchyroll.py') diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index aa258bbc2..cecd0c784 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -116,6 +116,10 @@ class CrunchyrollIE(CrunchyrollBaseIE): }, { 'url': 'http://www.crunchyroll.fr/girl-friend-beta/episode-11-goodbye-la-mode-661697', 'only_matching': True, + }, { + # geo-restricted (US), 18+ maturity wall, non-premium available + 'url': 'http://www.crunchyroll.com/cosplay-complex-ova/episode-1-the-birth-of-the-cosplay-club-565617', + 'only_matching': True, }] _FORMAT_IDS = { @@ -374,6 +378,19 @@ class CrunchyrollShowPlaylistIE(CrunchyrollBaseIE): 'title': 'A Bridge to the Starry Skies - Hoshizora e Kakaru Hashi' }, 'playlist_count': 13, + }, { + # geo-restricted (US), 18+ maturity wall, non-premium available + 'url': 'http://www.crunchyroll.com/cosplay-complex-ova', + 'info_dict': { + 'id': 'cosplay-complex-ova', + 'title': 'Cosplay Complex OVA' + }, + 'playlist_count': 3, + 'skip': 'Georestricted', + }, { + # geo-restricted (US), 18+ maturity wall, non-premium will be available since 2015.11.14 + 'url': 'http://www.crunchyroll.com/ladies-versus-butlers?skip_wall=1', + 'only_matching': True, }] def _real_extract(self, url): -- cgit v1.2.3 From 769078755318896fa1a6c5c8aba6f76d6aeddf78 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Thu, 22 Oct 2015 20:34:11 +0600 Subject: [crunchyroll] Improve subtitle regex (Closes #7262) --- youtube_dl/extractor/crunchyroll.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'youtube_dl/extractor/crunchyroll.py') diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index cecd0c784..f8ce10111 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -245,7 +245,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text def _get_subtitles(self, video_id, webpage): subtitles = {} - for sub_id, sub_name in re.findall(r'\?ssid=([0-9]+)" title="([^"]+)', webpage): + for sub_id, sub_name in re.findall(r'\bssid=([0-9]+)"[^>]+?\btitle="([^"]+)', webpage): sub_page = self._download_webpage( 'http://www.crunchyroll.com/xml/?req=RpcApiSubtitle_GetXml&subtitle_script_id=' + sub_id, video_id, note='Downloading subtitles for ' + sub_name) -- cgit v1.2.3 From 36e6f62cd0883f0f486d1666d010e5d9e6d515bd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?= Date: Sun, 25 Oct 2015 20:04:55 +0100 Subject: Use a wrapper around xml.etree.ElementTree.fromstring in python 2.x (#7178) Attributes aren't unicode objects, so they couldn't be directly used in info_dict fields (for example '--write-description' doesn't work with bytes). --- youtube_dl/extractor/crunchyroll.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'youtube_dl/extractor/crunchyroll.py') diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index f8ce10111..0c9b8ca02 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -5,12 +5,12 @@ import re import json import base64 import zlib -import xml.etree.ElementTree from hashlib import sha1 from math import pow, sqrt, floor from .common import InfoExtractor from ..compat import ( + compat_etree_fromstring, compat_urllib_parse, compat_urllib_parse_unquote, compat_urllib_request, @@ -234,7 +234,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text return output def _extract_subtitles(self, subtitle): - sub_root = xml.etree.ElementTree.fromstring(subtitle) + sub_root = compat_etree_fromstring(subtitle) return [{ 'ext': 'srt', 'data': self._convert_subtitles_to_srt(sub_root), -- cgit v1.2.3 From 5214f1e31d5e5ba692fb1ed4803ff71ef4e480e8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 7 Nov 2015 19:25:59 +0600 Subject: [crunchyroll] Fix title extraction (Closes #7396) --- youtube_dl/extractor/crunchyroll.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'youtube_dl/extractor/crunchyroll.py') diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index 0c9b8ca02..4243f3e2e 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -287,7 +287,9 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text if 'To view this, please log in to verify you are 18 or older.' in webpage: self.raise_login_required() - video_title = self._html_search_regex(r']*>(.+?)', webpage, 'video_title', flags=re.DOTALL) + video_title = self._html_search_regex( + r'(?s)]*>((?:(?!]+itemprop=["\']title["\'][^>]*>(?:(?!', + webpage, 'video_title') video_title = re.sub(r' {2,}', ' ', video_title) video_description = self._html_search_regex(r'"description":"([^"]+)', webpage, 'video_description', default='') if not video_description: -- cgit v1.2.3 From 2c740cf28d257d2a915195e7cc60f83e6690d2cc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 7 Nov 2015 19:29:09 +0600 Subject: [crunchyroll] Simplify description extraction --- youtube_dl/extractor/crunchyroll.py | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'youtube_dl/extractor/crunchyroll.py') diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index 4243f3e2e..9aa5d58b4 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -291,9 +291,8 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text r'(?s)]*>((?:(?!]+itemprop=["\']title["\'][^>]*>(?:(?!', webpage, 'video_title') video_title = re.sub(r' {2,}', ' ', video_title) - video_description = self._html_search_regex(r'"description":"([^"]+)', webpage, 'video_description', default='') - if not video_description: - video_description = None + video_description = self._html_search_regex( + r'"description":"([^"]+)', webpage, 'video_description', default=None) video_upload_date = self._html_search_regex( [r'
Availability for free users:(.+?)
', r'
[^<>]+\s*(.+?\d{4})\s*
'], webpage, 'video_upload_date', fatal=False, flags=re.DOTALL) -- cgit v1.2.3 From 6d02b9a392d39c114d3fb58bf7965f62196ccecd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 7 Nov 2015 20:02:39 +0600 Subject: [crunchyroll] Fix description extraction --- youtube_dl/extractor/crunchyroll.py | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'youtube_dl/extractor/crunchyroll.py') diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index 9aa5d58b4..6e5999c72 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -21,6 +21,7 @@ from ..utils import ( bytes_to_intlist, intlist_to_bytes, int_or_none, + lowercase_escape, remove_end, unified_strdate, urlencode_postdata, @@ -104,7 +105,7 @@ class CrunchyrollIE(CrunchyrollBaseIE): 'id': '589804', 'ext': 'flv', 'title': 'Culture Japan Episode 1 – Rebuilding Japan after the 3.11', - 'description': 'md5:fe2743efedb49d279552926d0bd0cd9e', + 'description': 'md5:2fbc01f90b87e8e9137296f37b461c12', 'thumbnail': 're:^https?://.*\.jpg$', 'uploader': 'Danny Choo Network', 'upload_date': '20120213', @@ -292,7 +293,10 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text webpage, 'video_title') video_title = re.sub(r' {2,}', ' ', video_title) video_description = self._html_search_regex( - r'"description":"([^"]+)', webpage, 'video_description', default=None) + r']*>\s*.+?\[media_id=%s\].+?"description"\s*:\s*"([^"]+)' % video_id, + webpage, 'description', default=None) + if video_description: + video_description = lowercase_escape(video_description.replace(r'\r\n', '\n')) video_upload_date = self._html_search_regex( [r'
Availability for free users:(.+?)
', r'
[^<>]+\s*(.+?\d{4})\s*
'], webpage, 'video_upload_date', fatal=False, flags=re.DOTALL) -- cgit v1.2.3 From 5c2266df4b9aeb7881ed8c026a038e2a25e43734 Mon Sep 17 00:00:00 2001 From: Sergey M? Date: Sat, 21 Nov 2015 22:18:17 +0600 Subject: Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8 --- youtube_dl/extractor/crunchyroll.py | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'youtube_dl/extractor/crunchyroll.py') diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index 6e5999c72..00d943f77 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -23,6 +23,7 @@ from ..utils import ( int_or_none, lowercase_escape, remove_end, + sanitized_Request, unified_strdate, urlencode_postdata, xpath_text, @@ -46,7 +47,7 @@ class CrunchyrollBaseIE(InfoExtractor): 'name': username, 'password': password, }) - login_request = compat_urllib_request.Request(login_url, data) + login_request = sanitized_Request(login_url, data) login_request.add_header('Content-Type', 'application/x-www-form-urlencoded') self._download_webpage(login_request, None, False, 'Wrong login info') @@ -55,7 +56,7 @@ class CrunchyrollBaseIE(InfoExtractor): def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5, encoding=None): request = (url_or_request if isinstance(url_or_request, compat_urllib_request.Request) - else compat_urllib_request.Request(url_or_request)) + else sanitized_Request(url_or_request)) # Accept-Language must be set explicitly to accept any language to avoid issues # similar to https://github.com/rg3/youtube-dl/issues/6797. # Along with IP address Crunchyroll uses Accept-Language to guess whether georestriction @@ -307,7 +308,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text 'video_uploader', fatal=False) playerdata_url = compat_urllib_parse_unquote(self._html_search_regex(r'"config_url":"([^"]+)', webpage, 'playerdata_url')) - playerdata_req = compat_urllib_request.Request(playerdata_url) + playerdata_req = sanitized_Request(playerdata_url) playerdata_req.data = compat_urllib_parse.urlencode({'current_page': webpage_url}) playerdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded') playerdata = self._download_webpage(playerdata_req, video_id, note='Downloading media info') @@ -319,7 +320,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text for fmt in re.findall(r'showmedia\.([0-9]{3,4})p', webpage): stream_quality, stream_format = self._FORMAT_IDS[fmt] video_format = fmt + 'p' - streamdata_req = compat_urllib_request.Request( + streamdata_req = sanitized_Request( 'http://www.crunchyroll.com/xml/?req=RpcApiVideoPlayer_GetStandardConfig&media_id=%s&video_format=%s&video_quality=%s' % (stream_id, stream_format, stream_quality), compat_urllib_parse.urlencode({'current_page': url}).encode('utf-8')) -- cgit v1.2.3