[smotri] Remove extractor (#27358)
authorAndrey Smirnoff <37037851+mashed-potatoes@users.noreply.github.com>
Wed, 9 Dec 2020 19:01:23 +0000 (00:01 +0500)
committerGitHub <noreply@github.com>
Wed, 9 Dec 2020 19:01:23 +0000 (02:01 +0700)
youtube_dl/extractor/extractors.py
youtube_dl/extractor/generic.py
youtube_dl/extractor/smotri.py [deleted file]
youtube_dl/options.py

index 3e6581adda9a7378588337a2106c72e76ce0405e..533c074b336454e78894be8d0a03c152599094ef 100644 (file)
@@ -1041,12 +1041,6 @@ from .sky import (
 from .slideshare import SlideshareIE
 from .slideslive import SlidesLiveIE
 from .slutload import SlutloadIE
-from .smotri import (
-    SmotriIE,
-    SmotriCommunityIE,
-    SmotriUserIE,
-    SmotriBroadcastIE,
-)
 from .snotr import SnotrIE
 from .sohu import SohuIE
 from .sonyliv import SonyLIVIE
index 9eba9614f79dc08947d194c89a0db76df34d981b..80ecaf7950006e283762cefcfc400f8ba45f8430 100644 (file)
@@ -52,7 +52,6 @@ from .ooyala import OoyalaIE
 from .rutv import RUTVIE
 from .tvc import TVCIE
 from .sportbox import SportBoxIE
-from .smotri import SmotriIE
 from .myvi import MyviIE
 from .condenast import CondeNastIE
 from .udn import UDNEmbedIE
@@ -2815,11 +2814,6 @@ class GenericIE(InfoExtractor):
         if mobj is not None:
             return self.url_result(mobj.group('url'))
 
-        # Look for embedded smotri.com player
-        smotri_url = SmotriIE._extract_url(webpage)
-        if smotri_url:
-            return self.url_result(smotri_url, 'Smotri')
-
         # Look for embedded Myvi.ru player
         myvi_url = MyviIE._extract_url(webpage)
         if myvi_url:
diff --git a/youtube_dl/extractor/smotri.py b/youtube_dl/extractor/smotri.py
deleted file mode 100644 (file)
index 45995f3..0000000
+++ /dev/null
@@ -1,416 +0,0 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
-import re
-import json
-import hashlib
-import uuid
-
-from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-    int_or_none,
-    sanitized_Request,
-    unified_strdate,
-    urlencode_postdata,
-    xpath_text,
-)
-
-
-class SmotriIE(InfoExtractor):
-    IE_DESC = 'Smotri.com'
-    IE_NAME = 'smotri'
-    _VALID_URL = r'https?://(?:www\.)?(?:smotri\.com/video/view/\?id=|pics\.smotri\.com/(?:player|scrubber_custom8)\.swf\?file=)(?P<id>v(?P<realvideoid>[0-9]+)[a-z0-9]{4})'
-    _NETRC_MACHINE = 'smotri'
-
-    _TESTS = [
-        # real video id 2610366
-        {
-            'url': 'http://smotri.com/video/view/?id=v261036632ab',
-            'md5': '02c0dfab2102984e9c5bb585cc7cc321',
-            'info_dict': {
-                'id': 'v261036632ab',
-                'ext': 'mp4',
-                'title': 'катастрофа с камер видеонаблюдения',
-                'uploader': 'rbc2008',
-                'uploader_id': 'rbc08',
-                'upload_date': '20131118',
-                'thumbnail': 'http://frame6.loadup.ru/8b/a9/2610366.3.3.jpg',
-            },
-        },
-        # real video id 57591
-        {
-            'url': 'http://smotri.com/video/view/?id=v57591cb20',
-            'md5': '830266dfc21f077eac5afd1883091bcd',
-            'info_dict': {
-                'id': 'v57591cb20',
-                'ext': 'flv',
-                'title': 'test',
-                'uploader': 'Support Photofile@photofile',
-                'uploader_id': 'support-photofile',
-                'upload_date': '20070704',
-                'thumbnail': 'http://frame4.loadup.ru/03/ed/57591.2.3.jpg',
-            },
-        },
-        # video-password, not approved by moderator
-        {
-            'url': 'http://smotri.com/video/view/?id=v1390466a13c',
-            'md5': 'f6331cef33cad65a0815ee482a54440b',
-            'info_dict': {
-                'id': 'v1390466a13c',
-                'ext': 'mp4',
-                'title': 'TOCCA_A_NOI_-_LE_COSE_NON_VANNO_CAMBIAMOLE_ORA-1',
-                'uploader': 'timoxa40',
-                'uploader_id': 'timoxa40',
-                'upload_date': '20100404',
-                'thumbnail': 'http://frame7.loadup.ru/af/3f/1390466.3.3.jpg',
-            },
-            'params': {
-                'videopassword': 'qwerty',
-            },
-            'skip': 'Video is not approved by moderator',
-        },
-        # video-password
-        {
-            'url': 'http://smotri.com/video/view/?id=v6984858774#',
-            'md5': 'f11e01d13ac676370fc3b95b9bda11b0',
-            'info_dict': {
-                'id': 'v6984858774',
-                'ext': 'mp4',
-                'title': 'Дача Солженицина ПАРОЛЬ 223322',
-                'uploader': 'psavari1',
-                'uploader_id': 'psavari1',
-                'upload_date': '20081103',
-                'thumbnail': r're:^https?://.*\.jpg$',
-            },
-            'params': {
-                'videopassword': '223322',
-            },
-        },
-        # age limit + video-password, not approved by moderator
-        {
-            'url': 'http://smotri.com/video/view/?id=v15408898bcf',
-            'md5': '91e909c9f0521adf5ee86fbe073aad70',
-            'info_dict': {
-                'id': 'v15408898bcf',
-                'ext': 'flv',
-                'title': 'этот ролик не покажут по ТВ',
-                'uploader': 'zzxxx',
-                'uploader_id': 'ueggb',
-                'upload_date': '20101001',
-                'thumbnail': 'http://frame3.loadup.ru/75/75/1540889.1.3.jpg',
-                'age_limit': 18,
-            },
-            'params': {
-                'videopassword': '333'
-            },
-            'skip': 'Video is not approved by moderator',
-        },
-        # age limit + video-password
-        {
-            'url': 'http://smotri.com/video/view/?id=v7780025814',
-            'md5': 'b4599b068422559374a59300c5337d72',
-            'info_dict': {
-                'id': 'v7780025814',
-                'ext': 'mp4',
-                'title': 'Sexy Beach (пароль 123)',
-                'uploader': 'вАся',
-                'uploader_id': 'asya_prosto',
-                'upload_date': '20081218',
-                'thumbnail': r're:^https?://.*\.jpg$',
-                'age_limit': 18,
-            },
-            'params': {
-                'videopassword': '123'
-            },
-        },
-        # swf player
-        {
-            'url': 'http://pics.smotri.com/scrubber_custom8.swf?file=v9188090500',
-            'md5': '31099eeb4bc906712c5f40092045108d',
-            'info_dict': {
-                'id': 'v9188090500',
-                'ext': 'mp4',
-                'title': 'Shakira - Don\'t Bother',
-                'uploader': 'HannahL',
-                'uploader_id': 'lisaha95',
-                'upload_date': '20090331',
-                'thumbnail': 'http://frame8.loadup.ru/44/0b/918809.7.3.jpg',
-            },
-        },
-    ]
-
-    @classmethod
-    def _extract_url(cls, webpage):
-        mobj = re.search(
-            r'<embed[^>]src=(["\'])(?P<url>http://pics\.smotri\.com/(?:player|scrubber_custom8)\.swf\?file=v.+?\1)',
-            webpage)
-        if mobj is not None:
-            return mobj.group('url')
-
-        mobj = re.search(
-            r'''(?x)<div\s+class="video_file">http://smotri\.com/video/download/file/[^<]+</div>\s*
-                    <div\s+class="video_image">[^<]+</div>\s*
-                    <div\s+class="video_id">(?P<id>[^<]+)</div>''', webpage)
-        if mobj is not None:
-            return 'http://smotri.com/video/view/?id=%s' % mobj.group('id')
-
-    def _search_meta(self, name, html, display_name=None):
-        if display_name is None:
-            display_name = name
-        return self._html_search_meta(name, html, display_name)
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        video_form = {
-            'ticket': video_id,
-            'video_url': '1',
-            'frame_url': '1',
-            'devid': 'LoadupFlashPlayer',
-            'getvideoinfo': '1',
-        }
-
-        video_password = self._downloader.params.get('videopassword')
-        if video_password:
-            video_form['pass'] = hashlib.md5(video_password.encode('utf-8')).hexdigest()
-
-        video = self._download_json(
-            'http://smotri.com/video/view/url/bot/',
-            video_id, 'Downloading video JSON',
-            data=urlencode_postdata(video_form),
-            headers={'Content-Type': 'application/x-www-form-urlencoded'})
-
-        video_url = video.get('_vidURL') or video.get('_vidURL_mp4')
-
-        if not video_url:
-            if video.get('_moderate_no'):
-                raise ExtractorError(
-                    'Video %s has not been approved by moderator' % video_id, expected=True)
-
-            if video.get('error'):
-                raise ExtractorError('Video %s does not exist' % video_id, expected=True)
-
-            if video.get('_pass_protected') == 1:
-                msg = ('Invalid video password' if video_password
-                       else 'This video is protected by a password, use the --video-password option')
-                raise ExtractorError(msg, expected=True)
-
-        title = video['title']
-        thumbnail = video.get('_imgURL')
-        upload_date = unified_strdate(video.get('added'))
-        uploader = video.get('userNick')
-        uploader_id = video.get('userLogin')
-        duration = int_or_none(video.get('duration'))
-
-        # Video JSON does not provide enough meta data
-        # We will extract some from the video web page instead
-        webpage_url = 'http://smotri.com/video/view/?id=%s' % video_id
-        webpage = self._download_webpage(webpage_url, video_id, 'Downloading video page')
-
-        # Warning if video is unavailable
-        warning = self._html_search_regex(
-            r'<div[^>]+class="videoUnModer"[^>]*>(.+?)</div>', webpage,
-            'warning message', default=None)
-        if warning is not None:
-            self._downloader.report_warning(
-                'Video %s may not be available; smotri said: %s ' %
-                (video_id, warning))
-
-        # Adult content
-        if 'EroConfirmText">' in webpage:
-            self.report_age_confirmation()
-            confirm_string = self._html_search_regex(
-                r'<a[^>]+href="/video/view/\?id=%s&confirm=([^"]+)"' % video_id,
-                webpage, 'confirm string')
-            confirm_url = webpage_url + '&confirm=%s' % confirm_string
-            webpage = self._download_webpage(
-                confirm_url, video_id,
-                'Downloading video page (age confirmed)')
-            adult_content = True
-        else:
-            adult_content = False
-
-        view_count = self._html_search_regex(
-            r'(?s)Общее количество просмотров.*?<span class="Number">(\d+)</span>',
-            webpage, 'view count', fatal=False)
-
-        return {
-            'id': video_id,
-            'url': video_url,
-            'title': title,
-            'thumbnail': thumbnail,
-            'uploader': uploader,
-            'upload_date': upload_date,
-            'uploader_id': uploader_id,
-            'duration': duration,
-            'view_count': int_or_none(view_count),
-            'age_limit': 18 if adult_content else 0,
-        }
-
-
-class SmotriCommunityIE(InfoExtractor):
-    IE_DESC = 'Smotri.com community videos'
-    IE_NAME = 'smotri:community'
-    _VALID_URL = r'https?://(?:www\.)?smotri\.com/community/video/(?P<id>[0-9A-Za-z_\'-]+)'
-    _TEST = {
-        'url': 'http://smotri.com/community/video/kommuna',
-        'info_dict': {
-            'id': 'kommuna',
-        },
-        'playlist_mincount': 4,
-    }
-
-    def _real_extract(self, url):
-        community_id = self._match_id(url)
-
-        rss = self._download_xml(
-            'http://smotri.com/export/rss/video/by/community/-/%s/video.xml' % community_id,
-            community_id, 'Downloading community RSS')
-
-        entries = [
-            self.url_result(video_url.text, SmotriIE.ie_key())
-            for video_url in rss.findall('./channel/item/link')]
-
-        return self.playlist_result(entries, community_id)
-
-
-class SmotriUserIE(InfoExtractor):
-    IE_DESC = 'Smotri.com user videos'
-    IE_NAME = 'smotri:user'
-    _VALID_URL = r'https?://(?:www\.)?smotri\.com/user/(?P<id>[0-9A-Za-z_\'-]+)'
-    _TESTS = [{
-        'url': 'http://smotri.com/user/inspector',
-        'info_dict': {
-            'id': 'inspector',
-            'title': 'Inspector',
-        },
-        'playlist_mincount': 9,
-    }]
-
-    def _real_extract(self, url):
-        user_id = self._match_id(url)
-
-        rss = self._download_xml(
-            'http://smotri.com/export/rss/user/video/-/%s/video.xml' % user_id,
-            user_id, 'Downloading user RSS')
-
-        entries = [self.url_result(video_url.text, 'Smotri')
-                   for video_url in rss.findall('./channel/item/link')]
-
-        description_text = xpath_text(rss, './channel/description') or ''
-        user_nickname = self._search_regex(
-            '^Видео режиссера (.+)$', description_text,
-            'user nickname', fatal=False)
-
-        return self.playlist_result(entries, user_id, user_nickname)
-
-
-class SmotriBroadcastIE(InfoExtractor):
-    IE_DESC = 'Smotri.com broadcasts'
-    IE_NAME = 'smotri:broadcast'
-    _VALID_URL = r'https?://(?:www\.)?(?P<url>smotri\.com/live/(?P<id>[^/]+))/?.*'
-    _NETRC_MACHINE = 'smotri'
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        broadcast_id = mobj.group('id')
-
-        broadcast_url = 'http://' + mobj.group('url')
-        broadcast_page = self._download_webpage(broadcast_url, broadcast_id, 'Downloading broadcast page')
-
-        if re.search('>Режиссер с логином <br/>"%s"<br/> <span>не существует<' % broadcast_id, broadcast_page) is not None:
-            raise ExtractorError(
-                'Broadcast %s does not exist' % broadcast_id, expected=True)
-
-        # Adult content
-        if re.search('EroConfirmText">', broadcast_page) is not None:
-
-            (username, password) = self._get_login_info()
-            if username is None:
-                self.raise_login_required(
-                    'Erotic broadcasts allowed only for registered users')
-
-            login_form = {
-                'login-hint53': '1',
-                'confirm_erotic': '1',
-                'login': username,
-                'password': password,
-            }
-
-            request = sanitized_Request(
-                broadcast_url + '/?no_redirect=1', urlencode_postdata(login_form))
-            request.add_header('Content-Type', 'application/x-www-form-urlencoded')
-            broadcast_page = self._download_webpage(
-                request, broadcast_id, 'Logging in and confirming age')
-
-            if '>Неверный логин или пароль<' in broadcast_page:
-                raise ExtractorError(
-                    'Unable to log in: bad username or password', expected=True)
-
-            adult_content = True
-        else:
-            adult_content = False
-
-        ticket = self._html_search_regex(
-            (r'data-user-file=(["\'])(?P<ticket>(?!\1).+)\1',
-             r"window\.broadcast_control\.addFlashVar\('file'\s*,\s*'(?P<ticket>[^']+)'\)"),
-            broadcast_page, 'broadcast ticket', group='ticket')
-
-        broadcast_url = 'http://smotri.com/broadcast/view/url/?ticket=%s' % ticket
-
-        broadcast_password = self._downloader.params.get('videopassword')
-        if broadcast_password:
-            broadcast_url += '&pass=%s' % hashlib.md5(broadcast_password.encode('utf-8')).hexdigest()
-
-        broadcast_json_page = self._download_webpage(
-            broadcast_url, broadcast_id, 'Downloading broadcast JSON')
-
-        try:
-            broadcast_json = json.loads(broadcast_json_page)
-
-            protected_broadcast = broadcast_json['_pass_protected'] == 1
-            if protected_broadcast and not broadcast_password:
-                raise ExtractorError(
-                    'This broadcast is protected by a password, use the --video-password option',
-                    expected=True)
-
-            broadcast_offline = broadcast_json['is_play'] == 0
-            if broadcast_offline:
-                raise ExtractorError('Broadcast %s is offline' % broadcast_id, expected=True)
-
-            rtmp_url = broadcast_json['_server']
-            mobj = re.search(r'^rtmp://[^/]+/(?P<app>.+)/?$', rtmp_url)
-            if not mobj:
-                raise ExtractorError('Unexpected broadcast rtmp URL')
-
-            broadcast_playpath = broadcast_json['_streamName']
-            broadcast_app = '%s/%s' % (mobj.group('app'), broadcast_json['_vidURL'])
-            broadcast_thumbnail = broadcast_json.get('_imgURL')
-            broadcast_title = self._live_title(broadcast_json['title'])
-            broadcast_description = broadcast_json.get('description')
-            broadcaster_nick = broadcast_json.get('nick')
-            broadcaster_login = broadcast_json.get('login')
-            rtmp_conn = 'S:%s' % uuid.uuid4().hex
-        except KeyError:
-            if protected_broadcast:
-                raise ExtractorError('Bad broadcast password', expected=True)
-            raise ExtractorError('Unexpected broadcast JSON')
-
-        return {
-            'id': broadcast_id,
-            'url': rtmp_url,
-            'title': broadcast_title,
-            'thumbnail': broadcast_thumbnail,
-            'description': broadcast_description,
-            'uploader': broadcaster_nick,
-            'uploader_id': broadcaster_login,
-            'age_limit': 18 if adult_content else 0,
-            'ext': 'flv',
-            'play_path': broadcast_playpath,
-            'player_url': 'http://pics.smotri.com/broadcast_play.swf',
-            'app': broadcast_app,
-            'rtmp_live': True,
-            'rtmp_conn': rtmp_conn,
-            'is_live': True,
-        }
index 6d5ac62b3bab68de226060c6bcd3cd9299f02825..3000ba41e7b02799acd4780558396c7f045207a0 100644 (file)
@@ -369,7 +369,7 @@ def parseOpts(overrideArguments=None):
     authentication.add_option(
         '--video-password',
         dest='videopassword', metavar='PASSWORD',
-        help='Video password (vimeo, smotri, youku)')
+        help='Video password (vimeo, youku)')
 
     adobe_pass = optparse.OptionGroup(parser, 'Adobe Pass Options')
     adobe_pass.add_option(