R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

[sproutvideo] Fix extractor

Browse Source
This commit is contained in:
thezero 2019-08-05 22:49:13 +02:00
parent 662087e491
commit 36071a8d06
5 changed files with 34 additions and 34 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
youtube_dl/downloader/__init__.py
View File

@ -43,9 +43,6 @@ def get_suitable_downloader(info_dict, params={}):
if ed.can_download(info_dict): if ed.can_download(info_dict):
return ed return ed
if info_dict.get('force_hlsdl') is True:
return HlsFD
if protocol.startswith('m3u8') and info_dict.get('is_live'): if protocol.startswith('m3u8') and info_dict.get('is_live'):
return FFmpegFD return FFmpegFD

3
youtube_dl/downloader/fragment.py
View File

@ -121,8 +121,6 @@ class FragmentFD(FileDownloader):
del ctx['fragment_filename_sanitized'] del ctx['fragment_filename_sanitized']
def _prepare_frag_download(self, ctx): def _prepare_frag_download(self, ctx):
if 'hls' not in ctx:
ctx['hls'] = False
if 'live' not in ctx: if 'live' not in ctx:
ctx['live'] = False ctx['live'] = False
if not ctx['live']: if not ctx['live']:
@ -145,7 +143,6 @@ class FragmentFD(FileDownloader):
'retries': self.params.get('retries', 0), 'retries': self.params.get('retries', 0),
'nopart': self.params.get('nopart', False), 'nopart': self.params.get('nopart', False),
'test': self.params.get('test', False), 'test': self.params.get('test', False),
'hls': ctx['hls'],
} }
) )
tmpfilename = self.temp_name(ctx['filename']) tmpfilename = self.temp_name(ctx['filename'])

7
youtube_dl/downloader/hls.py
View File

@ -105,7 +105,6 @@ class HlsFD(FragmentFD):
'filename': filename, 'filename': filename,
'total_frags': media_frags, 'total_frags': media_frags,
'ad_frags': ad_frags, 'ad_frags': ad_frags,
'hls': '#EXT-X-KEY:METHOD=AES-128' in s,
} }
self._prepare_and_start_frag_download(ctx) self._prepare_and_start_frag_download(ctx)
@ -176,8 +175,10 @@ class HlsFD(FragmentFD):
iv = decrypt_info.get('IV') or compat_struct_pack('>8xq', media_sequence) iv = decrypt_info.get('IV') or compat_struct_pack('>8xq', media_sequence)
decrypt_info['KEY'] = decrypt_info.get('KEY') or self.ydl.urlopen( decrypt_info['KEY'] = decrypt_info.get('KEY') or self.ydl.urlopen(
self._prepare_url(info_dict, info_dict.get('_decryption_key_url') or decrypt_info['URI'])).read() self._prepare_url(info_dict, info_dict.get('_decryption_key_url') or decrypt_info['URI'])).read()
frag_content = AES.new( # We don't decrypt fragments during the test
decrypt_info['KEY'], AES.MODE_CBC, iv).decrypt(frag_content) if not test:
frag_content = AES.new(
decrypt_info['KEY'], AES.MODE_CBC, iv).decrypt(frag_content)
self._append_fragment(ctx, frag_content) self._append_fragment(ctx, frag_content)
# We only download the first fragment during the test # We only download the first fragment during the test
if test: if test:

6
youtube_dl/downloader/http.py
View File

@ -45,8 +45,7 @@ class HttpFD(FileDownloader):
headers.update(add_headers) headers.update(add_headers)
is_test = self.params.get('test', False) is_test = self.params.get('test', False)
is_hls = self.params.get('hls', False) chunk_size = self._TEST_FILE_SIZE if is_test else (
chunk_size = self._TEST_FILE_SIZE if is_test and not is_hls else (
info_dict.get('downloader_options', {}).get('http_chunk_size') info_dict.get('downloader_options', {}).get('http_chunk_size')
or self.params.get('http_chunk_size') or 0) or self.params.get('http_chunk_size') or 0)
@ -195,8 +194,7 @@ class HttpFD(FileDownloader):
# However, for a test we still would like to download just a piece of a file. # However, for a test we still would like to download just a piece of a file.
# To achieve this we limit data_len to _TEST_FILE_SIZE and manually control # To achieve this we limit data_len to _TEST_FILE_SIZE and manually control
# block size when downloading a file. # block size when downloading a file.
# If we are using HLS we cannot cut the fragment because it will break the decryption. if is_test and (data_len is None or int(data_len) > self._TEST_FILE_SIZE):
if is_test and not is_hls and (data_len is None or int(data_len) > self._TEST_FILE_SIZE):
data_len = self._TEST_FILE_SIZE data_len = self._TEST_FILE_SIZE
if data_len is not None: if data_len is not None:

49
youtube_dl/extractor/sproutvideo.py
View File

@ -12,10 +12,11 @@ from ..compat import (
class SproutVideoIE(InfoExtractor): class SproutVideoIE(InfoExtractor):
_VALID_URL = r'(?:https?:|)//videos.sproutvideo.com/embed/(?P<id>[a-f0-9]+)/[a-f0-9]+\??.*' _NOSCHEMA_URL = r'//videos.sproutvideo.com/embed/(?P<id>[a-f0-9]+)/[a-f0-9]+'
_VALID_URL = r'https?:%s' % _NOSCHEMA_URL
_TEST = { _TEST = {
'url': 'https://videos.sproutvideo.com/embed/4c9dddb01910e3c9c4/0fc24387c4f24ee3', 'url': 'https://videos.sproutvideo.com/embed/4c9dddb01910e3c9c4/0fc24387c4f24ee3',
'md5': '1343ce1a6cb39d67889bfa07c7b02b0e', 'md5': 'fbc675bb97437e797d11d14d99563f50',
'info_dict': { 'info_dict': {
'id': '4c9dddb01910e3c9c4', 'id': '4c9dddb01910e3c9c4',
'ext': 'mp4', 'ext': 'mp4',
@ -26,9 +27,14 @@ class SproutVideoIE(InfoExtractor):
@staticmethod @staticmethod
def _extract_url(webpage): def _extract_url(webpage):
sproutvideo = re.search( sproutvideo = re.search(
r'(?:<iframe\s+class=[\'\"]sproutvideo-player.*src|href)=[\'\"](?P<url>%s)[\'\"]' % SproutVideoIE._VALID_URL, webpage) r'(?:<iframe\s+class=[\'\"]sproutvideo-player.*src|href)=[\'\"](?P<url>(?:https?:|)%s[^\'\"]+)[\'\"]' % SproutVideoIE._NOSCHEMA_URL, webpage)
if sproutvideo: if sproutvideo:
return sproutvideo.group('url') video_url = sproutvideo.group('url')
# Fix the video URL if the iframe doesn't have a defined schema
if video_url[:2] == '//':
video_url = 'https:' + video_url
return video_url
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
@ -42,30 +48,31 @@ class SproutVideoIE(InfoExtractor):
# signature->m for manifests # signature->m for manifests
# signature->k for keys # signature->k for keys
# signature->t for segments # signature->t for segments
m_sig = self._policy_to_qs(parsed_data, 'm') m_sign = self._policy_to_qs(parsed_data, 'm')
k_sig = self._policy_to_qs(parsed_data, 'k') k_sign = self._policy_to_qs(parsed_data, 'k')
t_sig = self._policy_to_qs(parsed_data, 't') t_sign = self._policy_to_qs(parsed_data, 't')
url = "https://{0}.videos.sproutvideo.com/{1}/{2}/video/index.m3u8?{3}" resource_url = 'https://{0}.videos.sproutvideo.com/{1}/{2}/video/index.m3u8?{3}'
url = url.format(parsed_data['base'], resource_url = resource_url.format(parsed_data['base'],
parsed_data['s3_user_hash'], parsed_data['s3_user_hash'],
parsed_data['s3_video_hash'], parsed_data['s3_video_hash'],
m_sig) m_sign)
formats = self._extract_m3u8_formats(url, video_id, 'mp4', 'm3u8_native', formats = self._extract_m3u8_formats(resource_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False) m3u8_id='hls', fatal=False)
self._sort_formats(formats) self._sort_formats(formats)
for i in range(len(formats)): for entry in formats:
formats[i]['url'] = "{}?{}".format(formats[i]['url'], m_sig) entry.update({
'url': '{0}?{1}'.format(entry['url'], m_sign),
'extra_param_to_segment_url': t_sign,
'extra_param_to_key_url': k_sign,
})
return { return {
'id': video_id, 'id': video_id,
'title': parsed_data['title'], 'title': parsed_data['title'],
'formats': formats, 'formats': formats,
'force_hlsdl': True, # currently FFmpeg is not supported
'extra_param_to_segment_url': t_sig,
'extra_param_to_key_url': k_sig
} }
def _format_qsdata(self, qs_data): def _format_qsdata(self, qs_data):
@ -75,6 +82,6 @@ class SproutVideoIE(InfoExtractor):
return parsed_dict return parsed_dict
def _policy_to_qs(self, policy, key): def _policy_to_qs(self, policy, key):
sig = self._format_qsdata(policy['signatures'][key]) sign = self._format_qsdata(policy['signatures'][key])
sig['sessionID'] = policy['sessionID'] sign['sessionID'] = policy['sessionID']
return compat_urllib_parse_urlencode(sig, doseq=True) return compat_urllib_parse_urlencode(sign, doseq=True)