v/youtube-dl
1
0
Fork 0
mirror of https://github.com/l1ving/youtube-dl synced 2020-11-18 19:53:54 -08:00
Code Issues Releases Wiki Activity

added all fixes

Browse Source 
more fixes

m3u8 format processing
This commit is contained in:
nimeir 2019-05-05 14:07:15 +01:00
parent a847d06337
commit e045ba67c3
1 changed files with 32 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

55
youtube_dl/extractor/rtp.py
View File

@ -3,9 +3,14 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re import re
import itertools
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import js_to_json from ..utils import (
determine_ext,
js_to_json,
update_url_query
)
class RTPIE(InfoExtractor): class RTPIE(InfoExtractor):
@ -41,18 +46,24 @@ class RTPIE(InfoExtractor):
r'(?s)RTPPlayer\(({.*?})', webpage, 'player config') r'(?s)RTPPlayer\(({.*?})', webpage, 'player config')
player_config = js_to_json(player_config) player_config = js_to_json(player_config)
config = self._parse_json(player_config, video_id) config = self._parse_json(player_config, video_id)
path, ext = config.get('file').rsplit('.', 1) path = config.get('file')
ext = determine_ext(path)
formats = [{ formats = [{
'format_id': 'rtmp',
'ext': ext, 'ext': ext,
'preference': -2, 'preference': -2,
'url': '{file}'.format(**config), 'url': path,
'app': config.get('application'), 'app': config.get('application'),
'play_path': '{ext:s}:{path:s}'.format(ext=ext, path=path),
'page_url': url, 'page_url': url,
'player_url': 'http://programas.rtp.pt/play/player.swf?v3', 'player_url': 'http://programas.rtp.pt/play/player.swf?v3',
'rtmp_real_time': True,
}] }]
if ext == 'm3u8':
m3u8_formats = self._extract_m3u8_formats(path, video_id)
for i in m3u8_formats:
i.update(formats[0])
i['ext'] = 'mp4'
formats = m3u8_formats
self._sort_formats(formats) self._sort_formats(formats)
return { return {
@ -65,29 +76,27 @@ class RTPIE(InfoExtractor):
class RTPPlaylistIE(InfoExtractor): class RTPPlaylistIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?rtp\.pt/play/p(?P<program_id>[0-9]+)(?!.+)' _VALID_URL = r'https?://(?:www\.)?rtp\.pt/play/p(?P<program_id>[0-9]+)'
def _get_program_id(self, url): def _get_program_id(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
program_id = mobj.group('program_id') program_id = mobj.group('program_id')
return program_id return program_id
def _extract_entries(self, url, program_id, page): def _extract_entries(self, url, program_id):
entry_url = "https://www.rtp.pt/play/bg_l_ep/?&listProgram=%s&listcategory=&listchannel=&type=radio&page=%s" % ( for page in itertools.count(1):
program_id, page query = update_url_query("https://www.rtp.pt/play/bg_l_ep/", {
) 'listProgram': program_id,
webpage = self._download_webpage(entry_url, program_id) 'type': 'radio',
return [self.url_result('https://www.rtp.pt/play/p%s/%s/' % (program_id, episode), 'RTP') 'page': page
for episode in re.findall(r'e\d+', webpage)] })
webpage = self._download_webpage(query, program_id, 'Downloading page %d' % page)
if not webpage:
break
for episode in re.findall(r'p%s/e(\d+)' % program_id, webpage):
yield self.url_result('https://www.rtp.pt/play/p%s/e%s/' % (program_id, episode), 'RTP')
def _real_extract(self, url): def _real_extract(self, url):
page = 1
program_id = self._get_program_id(url) program_id = self._get_program_id(url)
entry = self._extract_entries(url, program_id)
entry = self._extract_entries(url, program_id, page) return self.playlist_result(entry, playlist_id=program_id)
new_entry = self._extract_entries(url, program_id, page + 1)
while new_entry != []:
new_entry = self._extract_entries(url, program_id, page + 1)
entry += new_entry
page += 1
return self.playlist_result(entry, playlist_id=program_id)