[StreamsbIE] Add extractor for streamsb.com (viewsb.com) (#31517)

* Add extractor for streamsb.com (viewsb.com)

* make data url using app.js version

---------

Co-authored-by: dirkf <fieldhouse@gmx.net>

youtube_dl/extractor/extractors.py

@@ -376,6 +376,7 @@ from .fc2 import (
     FC2EmbedIE,
 )
 from .fczenit import FczenitIE
+from .filemoon import FileMoonIE
 from .fifa import FifaIE
 from .filmon import (
     FilmOnIE,
@@ -556,6 +557,7 @@ from .khanacademy import (
 from .kickstarter import KickStarterIE
 from .kinja import KinjaEmbedIE
 from .kinopoisk import KinoPoiskIE
+from .kommunetv import KommunetvIE
 from .konserthusetplay import KonserthusetPlayIE
 from .krasview import KrasViewIE
 from .kth import KTHIE
@@ -1204,6 +1206,7 @@ from .storyfire import (
 from .streamable import StreamableIE
 from .streamcloud import StreamcloudIE
 from .streamcz import StreamCZIE
+from .streamsb import StreamsbIE
 from .streetvoice import StreetVoiceIE
 from .stretchinternet import StretchInternetIE
 from .stv import STVPlayerIE

youtube_dl/extractor/filemoon.py

@@ -0,0 +1,43 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    decode_packed_codes,
+    js_to_json,
+)
+
+
+class FileMoonIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?filemoon\.sx/./(?P<id>\w+)'
+    _TEST = {
+        'url': 'https://filemoon.sx/e/dw40rxrzruqz',
+        'md5': '5a713742f57ac4aef29b74733e8dda01',
+        'info_dict': {
+            'id': 'dw40rxrzruqz',
+            'title': 'dw40rxrzruqz',
+            'ext': 'mp4'
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+        matches = re.findall(r'(?s)(eval.*?)</script>', webpage)
+        packed = matches[-1]
+        unpacked = decode_packed_codes(packed)
+        jwplayer_sources = self._parse_json(
+            self._search_regex(
+                r'(?s)player\s*\.\s*setup\s*\(\s*\{\s*sources\s*:\s*(.*?])', unpacked, 'jwplayer sources'),
+            video_id, transform_source=js_to_json)
+
+        formats = self._parse_jwplayer_formats(jwplayer_sources, video_id)
+
+        return {
+            'id': video_id,
+            'title': self._generic_title(url) or video_id,
+            'formats': formats
+        }

youtube_dl/extractor/kommunetv.py

@@ -0,0 +1,35 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import update_url
+
+
+class KommunetvIE(InfoExtractor):
+    _VALID_URL = r'https://(\w+).kommunetv.no/archive/(?P<id>\w+)'
+    _TEST = {
+        'url': 'https://oslo.kommunetv.no/archive/921',
+        'md5': '5f102be308ee759be1e12b63d5da4bbc',
+        'info_dict': {
+            'id': '921',
+            'title': 'Bystyremøte',
+            'ext': 'mp4'
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        headers = {
+            'Accept': 'application/json'
+        }
+        data = self._download_json('https://oslo.kommunetv.no/api/streams?streamType=1&id=%s' % video_id, video_id, headers=headers)
+        title = data['stream']['title']
+        file = data['playlist'][0]['playlist'][0]['file']
+        url = update_url(file, query=None, fragment=None)
+        formats = self._extract_m3u8_formats(url, video_id, ext='mp4', entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)
+        self._sort_formats(formats)
+        return {
+            'id': video_id,
+            'formats': formats,
+            'title': title
+        }

youtube_dl/extractor/streamsb.py

@@ -0,0 +1,61 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import binascii
+import random
+import re
+import string
+
+from .common import InfoExtractor
+from ..utils import urljoin, url_basename
+
+
+def to_ascii_hex(str1):
+    return binascii.hexlify(str1.encode('utf-8')).decode('ascii')
+
+
+def generate_random_string(length):
+    return ''.join(random.choice(string.ascii_letters + string.digits) for _ in range(length))
+
+
+class StreamsbIE(InfoExtractor):
+    _DOMAINS = ('viewsb.com', )
+    _VALID_URL = r'https://(?P<domain>%s)/(?P<id>.+)' % '|'.join(_DOMAINS)
+    _TEST = {
+        'url': 'https://viewsb.com/dxfvlu4qanjx',
+        'md5': '488d111a63415369bf90ea83adc8a325',
+        'info_dict': {
+            'id': 'dxfvlu4qanjx',
+            'ext': 'mp4',
+            'title': 'Sintel'
+        }
+    }
+
+    def _real_extract(self, url):
+        domain, video_id = re.match(self._VALID_URL, url).group('domain', 'id')
+        webpage = self._download_webpage(url, video_id)
+
+        iframe_rel_url = self._search_regex(r'''(?i)<iframe\b[^>]+\bsrc\s*=\s*('|")(?P<path>/.*\.html)\1''', webpage, 'iframe', group='path')
+        iframe_url = urljoin('https://' + domain, iframe_rel_url)
+
+        iframe_data = self._download_webpage(iframe_url, video_id)
+        app_version = self._search_regex(r'''<script\b[^>]+\bsrc\s*=\s*["|'].*/app\.min\.(\d+)\.js''', iframe_data, 'app version', fatal=False) or '50'
+
+        video_code = url_basename(iframe_url).rsplit('.')[0]
+
+        length = 12
+        req = '||'.join((generate_random_string(length), video_code, generate_random_string(length), 'streamsb'))
+        ereq = 'https://{0}/sources{1}/{2}'.format(domain, app_version, to_ascii_hex(req))
+
+        video_data = self._download_webpage(ereq, video_id, headers={
+            'Referer': iframe_url,
+            'watchsb': 'sbstream',
+        })
+        player_data = self._parse_json(video_data, video_id)
+        title = player_data['stream_data']['title']
+        formats = self._extract_m3u8_formats(player_data['stream_data']['file'], video_id, ext='mp4', entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)
+        return {
+            'id': video_id,
+            'formats': formats,
+            'title': title,
+        }