yt-dlp/youtube_dl/extractor/eighttracks.py

165 lines
5.7 KiB
Python
Raw Normal View History

2014-08-26 05:31:23 -04:00
# coding: utf-8
from __future__ import unicode_literals
2013-06-23 16:15:50 -04:00
import json
import random
from .common import InfoExtractor
from ..compat import (
2014-08-26 05:31:23 -04:00
compat_str,
2015-01-09 23:51:07 -05:00
)
from ..utils import (
2014-10-14 23:46:47 -04:00
ExtractorError,
2013-06-23 16:15:50 -04:00
)
class EightTracksIE(InfoExtractor):
IE_NAME = '8tracks'
_VALID_URL = r'https?://8tracks\.com/(?P<user>[^/]+)/(?P<id>[^/#]+)(?:#.*)?$'
2013-06-27 14:22:00 -04:00
_TEST = {
2014-08-26 05:31:23 -04:00
"name": "EightTracks",
"url": "http://8tracks.com/ytdl/youtube-dl-test-tracks-a",
"info_dict": {
'id': '1336550',
'display_id': 'youtube-dl-test-tracks-a',
"description": "test chars: \"'/\\ä↭",
"title": "youtube-dl test tracks \"'/\\ä↭<>",
},
"playlist": [
2013-06-27 14:22:00 -04:00
{
2014-08-26 05:31:23 -04:00
"md5": "96ce57f24389fc8734ce47f4c1abcc55",
"info_dict": {
"id": "11885610",
"ext": "m4a",
"title": "youtue-dl project<>\"' - youtube-dl test track 1 \"'/\\\u00e4\u21ad",
"uploader_id": "ytdl"
2013-06-27 14:22:00 -04:00
}
},
{
2014-08-26 05:31:23 -04:00
"md5": "4ab26f05c1f7291ea460a3920be8021f",
"info_dict": {
"id": "11885608",
"ext": "m4a",
"title": "youtube-dl project - youtube-dl test track 2 \"'/\\\u00e4\u21ad",
"uploader_id": "ytdl"
2013-06-27 14:22:00 -04:00
}
},
{
2014-08-26 05:31:23 -04:00
"md5": "d30b5b5f74217410f4689605c35d1fd7",
"info_dict": {
"id": "11885679",
"ext": "m4a",
"title": "youtube-dl project as well - youtube-dl test track 3 \"'/\\\u00e4\u21ad",
"uploader_id": "ytdl"
2013-06-27 14:22:00 -04:00
}
},
{
2014-08-26 05:31:23 -04:00
"md5": "4eb0a669317cd725f6bbd336a29f923a",
"info_dict": {
"id": "11885680",
"ext": "m4a",
"title": "youtube-dl project as well - youtube-dl test track 4 \"'/\\\u00e4\u21ad",
"uploader_id": "ytdl"
2013-06-27 14:22:00 -04:00
}
},
{
2014-08-26 05:31:23 -04:00
"md5": "1893e872e263a2705558d1d319ad19e8",
"info_dict": {
"id": "11885682",
"ext": "m4a",
"title": "PH - youtube-dl test track 5 \"'/\\\u00e4\u21ad",
"uploader_id": "ytdl"
2013-06-27 14:22:00 -04:00
}
},
{
2014-08-26 05:31:23 -04:00
"md5": "b673c46f47a216ab1741ae8836af5899",
"info_dict": {
"id": "11885683",
"ext": "m4a",
"title": "PH - youtube-dl test track 6 \"'/\\\u00e4\u21ad",
"uploader_id": "ytdl"
2013-06-27 14:22:00 -04:00
}
},
{
2014-08-26 05:31:23 -04:00
"md5": "1d74534e95df54986da7f5abf7d842b7",
"info_dict": {
"id": "11885684",
"ext": "m4a",
"title": "phihag - youtube-dl test track 7 \"'/\\\u00e4\u21ad",
"uploader_id": "ytdl"
2013-06-27 14:22:00 -04:00
}
},
{
2014-08-26 05:31:23 -04:00
"md5": "f081f47af8f6ae782ed131d38b9cd1c0",
"info_dict": {
"id": "11885685",
"ext": "m4a",
"title": "phihag - youtube-dl test track 8 \"'/\\\u00e4\u21ad",
"uploader_id": "ytdl"
2013-06-27 14:22:00 -04:00
}
}
]
}
2013-06-23 16:15:50 -04:00
def _real_extract(self, url):
2015-03-14 05:55:21 -04:00
playlist_id = self._match_id(url)
2013-06-23 16:15:50 -04:00
webpage = self._download_webpage(url, playlist_id)
2015-03-14 05:54:23 -04:00
data = self._parse_json(
self._search_regex(
r"(?s)PAGE\.mix\s*=\s*({.+?});\n", webpage, 'trax information'),
playlist_id)
2013-06-23 16:15:50 -04:00
session = str(random.randint(0, 1000000000))
mix_id = data['id']
track_count = data['tracks_count']
2014-10-14 23:46:47 -04:00
duration = data['duration']
2015-01-09 23:51:07 -05:00
avg_song_duration = float(duration) / track_count
# duration is sometimes negative, use predefined avg duration
if avg_song_duration <= 0:
avg_song_duration = 300
2013-06-23 16:15:50 -04:00
first_url = 'http://8tracks.com/sets/%s/play?player=sm&mix_id=%s&format=jsonh' % (session, mix_id)
next_url = first_url
2014-08-26 05:31:23 -04:00
entries = []
2014-10-14 23:46:47 -04:00
[8tracks] Use track count instead of looking at at_last_track property This fixes the error: $ youtube-dl http://8tracks.com/vladmc/counting-stars [8tracks] counting-stars: Downloading webpage [8tracks] counting-stars: Downloading song information 1/4 [8tracks] counting-stars: Downloading song information 2/4 [8tracks] counting-stars: Downloading song information 3/4 [8tracks] counting-stars: Downloading song information 4/4 [8tracks] counting-stars: Downloading song information 5/4 Traceback (most recent call last): File "/usr/lib/python2.7/runpy.py", line 162, in _run_module_as_main "__main__", fname, loader, pkg_name) File "/usr/lib/python2.7/runpy.py", line 72, in _run_code exec code in run_globals File "/home/phihag/projects/youtube-dl/youtube_dl/__main__.py", line 18, in <module> youtube_dl.main() File "/home/phihag/projects/youtube-dl/youtube_dl/__init__.py", line 761, in main _real_main(argv) File "/home/phihag/projects/youtube-dl/youtube_dl/__init__.py", line 714, in _real_main retcode = ydl.download(all_urls) File "/home/phihag/projects/youtube-dl/youtube_dl/YoutubeDL.py", line 701, in download videos = self.extract_info(url) File "/home/phihag/projects/youtube-dl/youtube_dl/YoutubeDL.py", line 342, in extract_info ie_result = ie.extract(url) File "/home/phihag/projects/youtube-dl/youtube_dl/extractor/common.py", line 121, in extract return self._real_extract(url) File "/home/phihag/projects/youtube-dl/youtube_dl/extractor/eighttracks.py", line 111, in _real_extract 'id': track_data['id'], KeyError: 'id'
2013-10-25 17:46:18 -04:00
for i in range(track_count):
2014-10-14 23:46:47 -04:00
api_json = None
download_tries = 0
while api_json is None:
try:
api_json = self._download_webpage(
next_url, playlist_id,
note='Downloading song information %d/%d' % (i + 1, track_count),
errnote='Failed to download song information')
except ExtractorError:
if download_tries > 3:
raise
else:
2014-12-06 02:20:35 -05:00
download_tries += 1
2015-01-09 23:51:07 -05:00
self._sleep(avg_song_duration, playlist_id)
2014-10-14 23:46:47 -04:00
2013-06-23 16:15:50 -04:00
api_data = json.loads(api_json)
2014-08-26 05:31:23 -04:00
track_data = api_data['set']['track']
2013-06-23 16:15:50 -04:00
info = {
2014-08-26 05:31:23 -04:00
'id': compat_str(track_data['id']),
2013-06-23 16:15:50 -04:00
'url': track_data['track_file_stream_url'],
2014-11-26 07:06:02 -05:00
'title': track_data['performer'] + ' - ' + track_data['name'],
2013-06-23 16:15:50 -04:00
'raw_title': track_data['name'],
'uploader_id': data['user']['login'],
'ext': 'm4a',
}
2014-08-26 05:31:23 -04:00
entries.append(info)
2014-10-14 23:46:47 -04:00
2014-08-26 05:31:23 -04:00
next_url = 'http://8tracks.com/sets/%s/next?player=sm&mix_id=%s&format=jsonh&track_id=%s' % (
session, mix_id, track_data['id'])
return {
'_type': 'playlist',
'entries': entries,
'id': compat_str(mix_id),
'display_id': playlist_id,
'title': data.get('name'),
'description': data.get('description'),
}