Madeorsk/youtube-dl
1
0
Fork 0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2025-02-17 01:17:54 +01:00
Code Issues Releases Wiki Activity

fixes after second review

Browse Source
This commit is contained in:
bato3 2018-07-14 14:42:04 +02:00
parent ccf6a90ba8
commit e887491de8
1 changed files with 63 additions and 52 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

115
youtube_dl/extractor/mp4upload.py
View File

@ -12,6 +12,7 @@ from ..utils import (
int_or_none, int_or_none,
float_or_none, float_or_none,
parse_filesize, parse_filesize,
parse_resolution,
strip_or_none, strip_or_none,
) )
from .common import InfoExtractor from .common import InfoExtractor
@ -35,6 +36,7 @@ class Mp4UploadIE(InfoExtractor):
'acodec': 'ffaac', 'acodec': 'ffaac',
'asr': 44100, 'asr': 44100,
'abr': 96, 'abr': 96,
'vbr': 266,
'upload_date': '20160702', 'upload_date': '20160702',
}, },
}, { }, {
@ -55,77 +57,86 @@ class Mp4UploadIE(InfoExtractor):
if not title: if not title:
raise ExtractorError('Title not found', expected=True, video_id=video_id) raise ExtractorError('Title not found', expected=True, video_id=video_id)
info_dict = { try:
'title': title, # It contains only `source url` and `thumbnail`
'id': video_id, jw_dict = self._extract_jwplayer_data(
} decode_packed_codes(
get_element_by_id(
embedpage = self._download_webpage(embed_url, video_id, note='Downloading embed webpage') 'player',
self._download_webpage(embed_url, video_id, note='Downloading embed webpage')
# It contains only `source url` and `thumbnail` )
poor_info_dict = self._extract_jwplayer_data( ).replace('\\\'', '"'),
decode_packed_codes( video_id, base_url=embed_url, require_title=False
get_element_by_id('player', embedpage) )
).replace('\\\'', '"'), except TypeError:
video_id, base_url=embed_url, require_title=False jw_dict = None
) if not jw_dict:
if not poor_info_dict:
raise ExtractorError('I can\'t find player data', video_id=video_id) raise ExtractorError('I can\'t find player data', video_id=video_id)
info_dict['thumbnail'] = poor_info_dict.get('thumbnail') acodec = None
_f = { asr = None
'url': poor_info_dict.get('formats', [{}])[0].get('url'), abr = None
'ext': poor_info_dict.get('formats', [{}])[0].get('ext'), audio_raw = self._html_search_regex(
'format_id': '1', r'<li><span class="infoname">Audio info:</span><span>(.+?)</span></li>',
} webpage, 'audioinfo', fatal=False)
if audio_raw:
audmatch = re.search(r'(.+?), (\d+) kbps, (\d+) Hz', audio_raw)
if audmatch:
(acodec, abr, asr) = audmatch.groups()
file_info = re.findall( resolution = {}
r'>(?P<label>[^<:]+):</span><span>(?P<value>[^<]+)</span></li>', resolution_raw = self._html_search_regex(
get_element_by_class('fileinfo', webpage) r'<li><span class="infoname">Resolution:</span><span>(.+?)</span></li>',
) webpage, 'resolution', fatal=False)
if file_info: if resolution_raw:
for info in file_info: resolution = parse_resolution(resolution_raw)
if info[0] == 'Codec':
_f['vcodec'] = info[1]
elif info[0] == 'Resolution': vcodec = self._html_search_regex(
_f['resolution'] = info[1].replace(' ', '') r'<li><span class="infoname">Codec:</span><span>(.+?)</span></li>',
resmatch = re.search(r'(?P<width>\d+)\s*x\s*(?P<height>\d+)', info[1]) webpage, 'codec', fatal=False)
if resmatch:
_f['width'] = int(resmatch.group('width'))
_f['height'] = int(resmatch.group('height'))
elif info[0] == 'Framerate': fps = self._html_search_regex(
fps = float_or_none(re.sub(r'[^\d\.]+', '', info[1])) r'<li><span class="infoname">Framerate:</span><span>(.+?) fps</span></li>',
if fps < 100: webpage, 'framerate', fatal=False)
_f['fps'] = fps
elif info[0] == 'Audio info': vbr = self._html_search_regex(
audmatch = re.search(r'(?P<acodec>.+?), (?P<abr>\d+) kbps, (?P<asr>\d+) Hz', info[1]) r'<li><span class="infoname">Bitrate:</span><span>(.+?) Kbps</span></li>',
if audmatch: webpage, 'framerate', fatal=False)
_f['acodec'] = audmatch.group('acodec')
_f['abr'] = int(audmatch.group('abr'))
_f['asr'] = int(audmatch.group('asr'))
elif info[0] == 'Bitrate': filesize_approx = parse_filesize(
_f['vbr'] = int_or_none(re.sub(r'\D+', '', info[1]))
_f['filesize_approx'] = parse_filesize(
self._html_search_regex( self._html_search_regex(
r'<span class="statd">Size</span>\s+<span>(.+?)</span>', r'<span class="statd">Size</span>\s+<span>(.+?)</span>',
webpage, 'filesize', fatal=False webpage, 'filesize', fatal=False
) )
) )
info_dict['formats'] = [_f]
timestamp = None
date_raw = self._search_regex(r'Uploaded on(.+?)</div>', webpage, 'timestamp', fatal=False, flags=re.DOTALL) date_raw = self._search_regex(r'Uploaded on(.+?)</div>', webpage, 'timestamp', fatal=False, flags=re.DOTALL)
if date_raw: if date_raw:
try: try:
info_dict['timestamp'] = time.mktime(time.strptime( timestamp = time.mktime(time.strptime(
re.sub(r'[^\d\-\:]+', '', date_raw), re.sub(r'[^\d\-\:]+', '', date_raw),
'%Y-%m-%d%H:%M:%S' '%Y-%m-%d%H:%M:%S'
)) ))
except ValueError: except ValueError:
pass pass
return info_dict return {
'title': title,
'id': video_id,
'thumbnail': jw_dict.get('thumbnail'),
'formats': [{
'url': jw_dict.get('formats', [{}])[0].get('url'),
'ext': jw_dict.get('formats', [{}])[0].get('ext'),
'filesize_approx': filesize_approx,
'vcodec': vcodec,
'width': resolution.get('width'),
'height': resolution.get('height'),
'fps': float_or_none(fps),
'acodec': acodec,
'abr': int_or_none(abr),
'asr': int_or_none(asr),
'vbr': int_or_none(vbr),
}],
'timestamp': timestamp,
}