Merge 5aee29b7ca into c5098961b0

Now also succeeds with player b12cc44b

test/test_jsinterp.py

@@ -425,6 +425,34 @@ class TestJSInterpreter(unittest.TestCase):
             self._test(jsi, [''], args=['', '-'])
             self._test(jsi, [], args=['', ''])
 
+    def test_slice(self):
+        self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice()}', [0, 1, 2, 3, 4, 5, 6, 7, 8])
+        self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(0)}', [0, 1, 2, 3, 4, 5, 6, 7, 8])
+        self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(5)}', [5, 6, 7, 8])
+        self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(99)}', [])
+        self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(-2)}', [7, 8])
+        self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(-99)}', [0, 1, 2, 3, 4, 5, 6, 7, 8])
+        self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(0, 0)}', [])
+        self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(1, 0)}', [])
+        self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(0, 1)}', [0])
+        self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(3, 6)}', [3, 4, 5])
+        self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(1, -1)}', [1, 2, 3, 4, 5, 6, 7])
+        self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(-1, 1)}', [])
+        self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(-3, -1)}', [6, 7])
+        self._test('function f(){return "012345678".slice()}', '012345678')
+        self._test('function f(){return "012345678".slice(0)}', '012345678')
+        self._test('function f(){return "012345678".slice(5)}', '5678')
+        self._test('function f(){return "012345678".slice(99)}', '')
+        self._test('function f(){return "012345678".slice(-2)}', '78')
+        self._test('function f(){return "012345678".slice(-99)}', '012345678')
+        self._test('function f(){return "012345678".slice(0, 0)}', '')
+        self._test('function f(){return "012345678".slice(1, 0)}', '')
+        self._test('function f(){return "012345678".slice(0, 1)}', '0')
+        self._test('function f(){return "012345678".slice(3, 6)}', '345')
+        self._test('function f(){return "012345678".slice(1, -1)}', '1234567')
+        self._test('function f(){return "012345678".slice(-1, 1)}', '')
+        self._test('function f(){return "012345678".slice(-3, -1)}', '67')
+
 
 if __name__ == '__main__':
     unittest.main()

test/test_youtube_signature.py

@@ -174,6 +174,14 @@ _NSIG_TESTS = [
         'https://www.youtube.com/s/player/5604538d/player_ias.vflset/en_US/base.js',
         '7X-he4jjvMx7BCX', 'sViSydX8IHtdWA',
     ),
+    (
+        'https://www.youtube.com/s/player/20dfca59/player_ias.vflset/en_US/base.js',
+        '-fLCxedkAk4LUTK2', 'O8kfRq1y1eyHGw',
+    ),
+    (
+        'https://www.youtube.com/s/player/b12cc44b/player_ias.vflset/en_US/base.js',
+        'keLa5R2U00sR9SQK', 'N1OGyujjEwMnLw',
+    ),
 ]
 
 

youtube_dl/extractor/senateisvp.py

@@ -5,48 +5,52 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
+    parse_duration,
     unsmuggle_url,
+    url_or_none,
 )
-from ..compat import (
+from ..compat import compat_parse_qs
-    compat_parse_qs,
-    compat_urlparse,
-)
 
 
 class SenateISVPIE(InfoExtractor):
+
+    # [committee, stream_number, stream_domain, stream_id, msl3]
     _COMM_MAP = [
-        ['ag', '76440', 'http://ag-f.akamaihd.net'],
+        ['ag', '76440', 'http://ag-f.akamaihd.net', '2036803', 'agriculture'],
-        ['aging', '76442', 'http://aging-f.akamaihd.net'],
+        ['aging', '76442', 'http://aging-f.akamaihd.net', '2036801', 'aging'],
-        ['approps', '76441', 'http://approps-f.akamaihd.net'],
+        ['approps', '76441', 'http://approps-f.akamaihd.net', '2036802', 'appropriations'],
-        ['armed', '76445', 'http://armed-f.akamaihd.net'],
+        ['armed', '76445', 'http://armed-f.akamaihd.net', '2036800', 'armedservices'],
-        ['banking', '76446', 'http://banking-f.akamaihd.net'],
+        ['banking', '76446', 'http://banking-f.akamaihd.net', '2036799', 'banking'],
-        ['budget', '76447', 'http://budget-f.akamaihd.net'],
+        ['budget', '76447', 'http://budget-f.akamaihd.net', '2036798', 'budget'],
-        ['cecc', '76486', 'http://srs-f.akamaihd.net'],
+        ['cecc', '76486', 'http://srs-f.akamaihd.net', '2036782', 'srs_cecc'],
-        ['commerce', '80177', 'http://commerce1-f.akamaihd.net'],
+        ['commerce', '80177', 'http://commerce1-f.akamaihd.net', '2036779', 'commerce'],
-        ['csce', '75229', 'http://srs-f.akamaihd.net'],
+        ['csce', '75229', 'http://srs-f.akamaihd.net', '2036777', 'srs_srs'],
-        ['dpc', '76590', 'http://dpc-f.akamaihd.net'],
+        ['dpc', '76590', 'http://dpc-f.akamaihd.net', None, 'dpc'],
-        ['energy', '76448', 'http://energy-f.akamaihd.net'],
+        ['energy', '76448', 'http://energy-f.akamaihd.net', '2036797', 'energy'],
-        ['epw', '76478', 'http://epw-f.akamaihd.net'],
+        ['epw', '76478', 'http://epw-f.akamaihd.net', '2036783', 'environment'],
-        ['ethics', '76449', 'http://ethics-f.akamaihd.net'],
+        ['ethics', '76449', 'http://ethics-f.akamaihd.net', '2036796', 'ethics'],
-        ['finance', '76450', 'http://finance-f.akamaihd.net'],
+        ['finance', '76450', 'http://finance-f.akamaihd.net', '2036795', 'finance_finance'],
-        ['foreign', '76451', 'http://foreign-f.akamaihd.net'],
+        ['foreign', '76451', 'http://foreign-f.akamaihd.net', '2036794', 'foreignrelations'],
-        ['govtaff', '76453', 'http://govtaff-f.akamaihd.net'],
+        ['govtaff', '76453', 'http://govtaff-f.akamaihd.net', '2036792', 'hsgac'],
-        ['help', '76452', 'http://help-f.akamaihd.net'],
+        ['help', '76452', 'http://help-f.akamaihd.net', '2036793', 'help'],
-        ['indian', '76455', 'http://indian-f.akamaihd.net'],
+        ['indian', '76455', 'http://indian-f.akamaihd.net', '2036791', 'indianaffairs'],
-        ['intel', '76456', 'http://intel-f.akamaihd.net'],
+        ['intel', '76456', 'http://intel-f.akamaihd.net', '2036790', 'intelligence'],
-        ['intlnarc', '76457', 'http://intlnarc-f.akamaihd.net'],
+        ['intlnarc', '76457', 'http://intlnarc-f.akamaihd.net', None, 'internationalnarcoticscaucus'],
-        ['jccic', '85180', 'http://jccic-f.akamaihd.net'],
+        ['jccic', '85180', 'http://jccic-f.akamaihd.net', '2036778', 'jccic'],
-        ['jec', '76458', 'http://jec-f.akamaihd.net'],
+        ['jec', '76458', 'http://jec-f.akamaihd.net', '2036789', 'jointeconomic'],
-        ['judiciary', '76459', 'http://judiciary-f.akamaihd.net'],
+        ['judiciary', '76459', 'http://judiciary-f.akamaihd.net', '2036788', 'judiciary'],
-        ['rpc', '76591', 'http://rpc-f.akamaihd.net'],
+        ['rpc', '76591', 'http://rpc-f.akamaihd.net', None, 'rpc'],
-        ['rules', '76460', 'http://rules-f.akamaihd.net'],
+        ['rules', '76460', 'http://rules-f.akamaihd.net', '2036787', 'rules'],
-        ['saa', '76489', 'http://srs-f.akamaihd.net'],
+        ['saa', '76489', 'http://srs-f.akamaihd.net', '2036780', 'srs_saa'],
-        ['smbiz', '76461', 'http://smbiz-f.akamaihd.net'],
+        ['smbiz', '76461', 'http://smbiz-f.akamaihd.net', '2036786', 'smallbusiness'],
-        ['srs', '75229', 'http://srs-f.akamaihd.net'],
+        ['srs', '75229', 'http://srs-f.akamaihd.net', '2031966', 'srs_srs'],
-        ['uscc', '76487', 'http://srs-f.akamaihd.net'],
+        ['uscc', '76487', 'http://srs-f.akamaihd.net', '2036781', 'srs_uscc'],
-        ['vetaff', '76462', 'http://vetaff-f.akamaihd.net'],
+        ['vetaff', '76462', 'http://vetaff-f.akamaihd.net', '2036785', 'veteransaffairs'],
-        ['arch', '', 'http://ussenate-f.akamaihd.net/']
+        ['arch', '', 'http://ussenate-f.akamaihd.net/', None, None],
+        ['uscp', None, '', '2043685', 'uscp'],
+        ['cio', None, '', '2043686', 'cio']
     ]
+
     _IE_NAME = 'senate.gov'
     _VALID_URL = r'https?://(?:www\.)?senate\.gov/isvp/?\?(?P<qs>.+)'
     _TESTS = [{
@@ -54,100 +58,120 @@ class SenateISVPIE(InfoExtractor):
         'info_dict': {
             'id': 'judiciary031715',
             'ext': 'mp4',
-            'title': 'Integrated Senate Video Player',
+            'title': 'judiciary031715',
-            'thumbnail': r're:^https?://.*\.(?:jpg|png)$',
+            'thumbnail': 'http://www.judiciary.senate.gov/themes/judiciary/images/video-poster-flash-fit.png',
-        },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
-        },
-    }, {
-        'url': 'http://www.senate.gov/isvp/?type=live&comm=commerce&filename=commerce011514.mp4&auto_play=false',
-        'info_dict': {
-            'id': 'commerce011514',
-            'ext': 'mp4',
-            'title': 'Integrated Senate Video Player'
-        },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
         },
+        'expected_warnings': ['Failed to download m3u8 information: HTTP Error 404: Not Found'],
     }, {
         'url': 'http://www.senate.gov/isvp/?type=arch&comm=intel&filename=intel090613&hc_location=ufi',
-        # checksum differs each time
         'info_dict': {
             'id': 'intel090613',
             'ext': 'mp4',
-            'title': 'Integrated Senate Video Player'
+            'title': 'intel090613',
-        }
+        },
+        'expected_warnings': ['Failed to download m3u8 information: HTTP Error 404: Not Found'],
     }, {
-        # From http://www.c-span.org/video/?96791-1
+        'url': 'https://www.senate.gov/isvp/?comm=govtaff&type=archv&stt=975&filename=govtaff111722&auto_play=false&poster=https%3A%2F%2Fwww%2Ehsgac%2Esenate%2Egov%2Fimages%2Fvideo%2Dposter%2Dflash%2Dfit%2Epng',
-        'url': 'http://www.senate.gov/isvp?type=live&comm=banking&filename=banking012715',
+        'info_dict': {
-        'only_matching': True,
+            'id': 'govtaff111722',
+            'ext': 'mp4',
+            'title': 'govtaff111722',
+            'thumbnail': 'https://www.hsgac.senate.gov/images/video-poster-flash-fit.png',
+        },
+    }, {
+        'url': 'https://www.senate.gov/isvp/?type=arch&comm=energy&filename=energy111722&stt=00:22:30&auto_play=false&wmode=transparent&poster=https%3A%2F%2Fwww%2Eenergy%2Esenate%2Egov%2Fthemes%2Fenergy%2Fimages%2Fvideo%2Dposter%2Dflash%2Dfit%2Epng',
+        'info_dict': {
+            'id': 'energy111722',
+            'ext': 'mp4',
+            'title': 'energy111722',
+            'thumbnail': 'https://www.energy.senate.gov/themes/energy/images/video-poster-flash-fit.png',
+        },
+    }, {
+        'url': 'https://www.senate.gov/isvp/?comm=foreign&type=archv&stt=0&filename=foreign080322&auto_play=false&wmode=transparent&poster=https%3A%2F%2Fwww%2Eforeign%2Esenate%2Egov%2Fthemes%2Fforeign%2Fimages%2Fvideo%2Dposter%2Dflash%2Dfit%2Epng',
+        'info_dict': {
+            'id': 'foreign080322',
+            'ext': 'mp4',
+            'title': 'foreign080322',
+            'thumbnail': 'https://www.foreign.senate.gov/themes/foreign/images/video-poster-flash-fit.png',
+        },
     }]
 
     @staticmethod
+    # returns url from an iframe
     def _search_iframe_url(webpage):
         mobj = re.search(
-            r"<iframe[^>]+src=['\"](?P<url>https?://www\.senate\.gov/isvp/?\?[^'\"]+)['\"]",
+            r'''<iframe\b[^>]+\bsrc\s*=\s*(['"])(?P<url>https?://www\.senate\.gov/isvp/?\?(?:(?!\1)\S)+)''',
             webpage)
         if mobj:
             return mobj.group('url')
 
+    @staticmethod
+    def __dictify(cm):
+        return dict((row[0], (row[1:] + ['', ''])[:4]) for row in cm)
+
+    # returns stream_number, stream_domain, stream_id, msl3
     def _get_info_for_comm(self, committee):
-        for entry in self._COMM_MAP:
+        dict = self.__dictify(self._COMM_MAP)
-            if entry[0] == committee:
+        return dict[committee][0:]
-                return entry[1:]
 
     def _real_extract(self, url):
+        # smuggled data may contain a forced title that should be used
         url, smuggled_data = unsmuggle_url(url, {})
-
         qs = compat_parse_qs(re.match(self._VALID_URL, url).group('qs'))
-        if not qs.get('filename') or not qs.get('type') or not qs.get('comm'):
-            raise ExtractorError('Invalid URL', expected=True)
 
-        video_id = re.sub(r'.mp4$', '', qs['filename'][0])
+        # error handling for invalid URL - specify which error
+        if not qs.get('filename'):
+            raise ExtractorError('Invalid URL. Missing filename in query parameters', expected=True)
+        if not qs.get('comm'):
+            raise ExtractorError('Invalid URL. Missing committee in query parameters', expected=True)
 
-        webpage = self._download_webpage(url, video_id)
+        committee = qs.get('comm')[0]
+        filename = qs.get('filename')[0]
+        video_id = re.sub(r'\.mp4$', '', filename)
 
-        if smuggled_data.get('force_title'):
+        # there is no point in pulling the title from the webpage since it always defaults to 'Integrated Senate Player'
-            title = smuggled_data['force_title']
+        title = smuggled_data.get('force_title') or filename
-        else:
-            title = self._html_search_regex(r'<title>([^<]+)</title>', webpage, video_id)
-        poster = qs.get('poster')
-        thumbnail = poster[0] if poster else None
 
-        video_type = qs['type'][0]
+        stream_number, stream_domain, stream_id, msl3 = self._get_info_for_comm(committee)
-        committee = video_type if video_type == 'arch' else qs['comm'][0]
+        stream_number = int(stream_number)
-        stream_num, domain = self._get_info_for_comm(committee)
+        stream_id = int(stream_id)
 
+        # the possible locations for the video: only the first has been seen in use
+        possible_manifest_urls = [
+            'https://www-senate-gov-media-srs.akamaized.net/hls/live/%d/%s/%s/master.m3u8' % (stream_id, committee, filename),
+            'https://www-senate-gov-msl3archive.akamaized.net/%s/%s_1/master.m3u8' % (msl3, filename),
+            '%s/i/%s_1@%d/master.m3u8' % (stream_domain, filename, stream_number),
+            'https://ussenate-f.akamaihd.net/i/%s.mp4/master.m3u8' % video_id,
+        ]
+
+        # we iterate through the possible locations until we find formats
         formats = []
-        if video_type == 'arch':
+        for url in possible_manifest_urls:
-            filename = video_id if '.' in video_id else video_id + '.mp4'
+            entries = self._extract_m3u8_formats(
-            formats = [{
+                url, video_id, ext='mp4', m3u8_id='hls',
-                # All parameters in the query string are necessary to prevent a 403 error
+                entry_protocol='m3u8_native', fatal=False)
-                'url': compat_urlparse.urljoin(domain, filename) + '?v=3.1.0&fp=&r=&g=',
+
-            }]
+            for entry in entries:
-        else:
+                mobj = re.search(r'(?P<tag>-[pb]).m3u8', entry['url'])
-            hdcore_sign = 'hdcore=3.1.0'
-            url_params = (domain, video_id, stream_num)
-            f4m_url = '%s/z/%s_1@%s/manifest.f4m?' % url_params + hdcore_sign
-            m3u8_url = '%s/i/%s_1@%s/master.m3u8' % url_params
-            for entry in self._extract_f4m_formats(f4m_url, video_id, f4m_id='f4m'):
-                # URLs without the extra param induce an 404 error
-                entry.update({'extra_param_to_segment_url': hdcore_sign})
-                formats.append(entry)
-            for entry in self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4', m3u8_id='m3u8'):
-                mobj = re.search(r'(?P<tag>(?:-p|-b)).m3u8', entry['url'])
                 if mobj:
                     entry['format_id'] += mobj.group('tag')
                 formats.append(entry)
 
-            self._sort_formats(formats)
+            if formats:
+                break
+
+        self._sort_formats(formats)
+        thumbnail = url_or_none(qs.get('poster', [None])[-1])
+        start_time = parse_duration(qs.get('stt', [None])[-1])
+        stop_time = parse_duration(qs.get('dur', [None])[-1])
+        if stop_time is not None:
+            stop_time += start_time or 0
 
         return {
             'id': video_id,
             'title': title,
             'formats': formats,
             'thumbnail': thumbnail,
+            'start_time': start_time,
+            'stop_time': stop_time,
         }

youtube_dl/extractor/youtube.py

@@ -1659,17 +1659,46 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
     def _extract_n_function_name(self, jscode):
         func_name, idx = self._search_regex(
             # new: (b=String.fromCharCode(110),c=a.get(b))&&c=nfunc[idx](c)
-            # or:  (b="nn"[+a.D],c=a.get(b))&&(c=nfunc[idx](c)s
+            # or:  (b="nn"[+a.D],c=a.get(b))&&(c=nfunc[idx](c)
-            # old: .get("n"))&&(b=nfunc[idx](b)
+            # or:  (PL(a),b=a.j.n||null)&&(b=nfunc[idx](b)
-            # older: .get("n"))&&(b=nfunc(b)
+            # or:  (b="nn"[+a.D],vL(a),c=a.j[b]||null)&&(c=narray[idx](c),a.set(b,c),narray.length||nfunc("")
+            # old: (b=a.get("n"))&&(b=nfunc[idx](b)(?P<c>[a-z])\s*=\s*[a-z]\s*
+            # older: (b=a.get("n"))&&(b=nfunc(b)
             r'''(?x)
-                (?:\(\s*(?P<b>[a-z])\s*=\s*(?:
+                \((?:[\w$()\s]+,)*?\s*      # (
-                    String\s*\.\s*fromCharCode\s*\(\s*110\s*\)|
+                (?P<b>[a-z])\s*=\s*         # b=
-                    "n+"\[\s*\+?s*[\w$.]+\s*]
+                (?:
-                )\s*,(?P<c>[a-z])\s*=\s*[a-z]\s*)?
+                    (?:                     # expect ,c=a.get(b) (etc)
-                \.\s*get\s*\(\s*(?(b)(?P=b)|"n{1,2}")(?:\s*\)){2}\s*&&\s*\(\s*(?(c)(?P=c)|b)\s*=\s*
+                        String\s*\.\s*fromCharCode\s*\(\s*110\s*\)|
-                (?P<nfunc>[a-zA-Z_$][\w$]*)(?:\s*\[(?P<idx>\d+)\])?\s*\(\s*[\w$]+\s*\)
+                        "n+"\[\s*\+?s*[\w$.]+\s*]
-            ''', jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
+                    )\s*(?:,[\w$()\s]+(?=,))*|
+                       (?P<old>[\w$]+)      # a (old[er])
+                   )\s*
+                   (?(old)
+                                            # b.get("n")
+                       (?:\.\s*[\w$]+\s*|\[\s*[\w$]+\s*]\s*)*?
+                       (?:\.\s*n|\[\s*"n"\s*]|\.\s*get\s*\(\s*"n"\s*\))
+                       |                    # ,c=a.get(b)
+                       ,\s*(?P<c>[a-z])\s*=\s*[a-z]\s*
+                       (?:\.\s*[\w$]+\s*|\[\s*[\w$]+\s*]\s*)*?
+                       (?:\[\s*(?P=b)\s*]|\.\s*get\s*\(\s*(?P=b)\s*\))
+                   )
+                                            # interstitial junk
+                   \s*(?:\|\|\s*null\s*)?(?:\)\s*)?&&\s*(?:\(\s*)?
+               (?(c)(?P=c)|(?P=b))\s*=\s*   # [c|b]=
+                                            # nfunc|nfunc[idx]
+                   (?P<nfunc>[a-zA-Z_$][\w$]*)(?:\s*\[(?P<idx>\d+)\])?\s*\(\s*[\w$]+\s*\)
+            ''', jscode, 'Initial JS player n function name', group=('nfunc', 'idx'),
+            default=(None, None))
+        # thx bashonly: yt-dlp/yt-dlp/pull/10611
+        if not func_name:
+            self.report_warning('Falling back to generic n function search')
+            return self._search_regex(
+                r'''(?xs)
+                    (?:(?<=[^\w$])|^)       # instead of \b, which ignores $
+                    (?P<name>(?!\d)[a-zA-Z\d_$]+)\s*=\s*function\((?!\d)[a-zA-Z\d_$]+\)
+                    \s*\{(?:(?!};).)+?["']enhanced_except_
+                ''', jscode, 'Initial JS player n function name', group='name')
         if not idx:
             return func_name
 

youtube_dl/jsinterp.py

@@ -925,9 +925,16 @@ class JSInterpreter(object):
                     obj.reverse()
                     return obj
                 elif member == 'slice':
-                    assertion(isinstance(obj, list), 'must be applied on a list')
+                    assertion(isinstance(obj, (list, compat_str)), 'must be applied on a list or string')
-                    assertion(len(argvals) == 1, 'takes exactly one argument')
+                    # From [1]:
-                    return obj[argvals[0]:]
+                    # .slice() - like [:]
+                    # .slice(n) - like [n:] (not [slice(n)]
+                    # .slice(m, n) - like [m:n] or [slice(m, n)]
+                    # [1] https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/Array/slice
+                    assertion(len(argvals) <= 2, 'takes between 0 and 2 arguments')
+                    if len(argvals) < 2:
+                        argvals += (None,)
+                    return obj[slice(*argvals)]
                 elif member == 'splice':
                     assertion(isinstance(obj, list), 'must be applied on a list')
                     assertion(argvals, 'takes one or more arguments')