Mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-08 04:02:40 +01:00
Code Issues Releases Activity

[beatenpro] Simplify and improve

Browse Source
This commit is contained in:
Sergey M․ 2015-03-13 22:01:15 +06:00
parent 1b53778175
commit 517bcca299
1 changed files with 16 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
youtube_dl/extractor/beatportpro.py
View File

@ -1,14 +1,15 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
from .common import InfoExtractor
import re import re
import json import json
from .common import InfoExtractor
from ..utils import int_or_none
class BeatportProIE(InfoExtractor): class BeatportProIE(InfoExtractor):
_VALID_URL = r'https?://pro\.beatport\.com/track/.*/(?P<id>[0-9]+)' _VALID_URL = r'https?://pro\.beatport\.com/track/.+/(?P<id>[0-9]+)'
_TESTS = [{ _TESTS = [{
'url': 'https://pro.beatport.com/track/synesthesia-original-mix/5379371', 'url': 'https://pro.beatport.com/track/synesthesia-original-mix/5379371',
'md5': 'b3c34d8639a2f6a7f734382358478887', 'md5': 'b3c34d8639a2f6a7f734382358478887',
@ -42,20 +43,17 @@ def _real_extract(self, url):
track_id = self._match_id(url) track_id = self._match_id(url)
webpage = self._download_webpage(url, track_id) webpage = self._download_webpage(url, track_id)
# Extract "Playables" JSON information from the page playables = self._search_regex(
playables = self._search_regex(r'window\.Playables = ({.*?});', webpage, r'window\.Playables\s*=\s*({.*?});', webpage,
'playables info', flags=re.DOTALL) 'playables info', flags=re.DOTALL)
playables = json.loads(playables) playables = json.loads(playables)
# Find first track with matching ID (always the first one listed?)
track = next(t for t in playables['tracks'] if t['id'] == int(track_id)) track = next(t for t in playables['tracks'] if t['id'] == int(track_id))
# Construct title from artist(s), track name, and mix name
title = ', '.join((a['name'] for a in track['artists'])) + ' - ' + track['name'] title = ', '.join((a['name'] for a in track['artists'])) + ' - ' + track['name']
if track['mix']: if track['mix']:
title += ' (' + track['mix'] + ')' title += ' (' + track['mix'] + ')'
# Get format information
formats = [] formats = []
for ext, info in track['preview'].items(): for ext, info in track['preview'].items():
if info['url'] is None: if info['url'] is None:
@ -76,26 +74,26 @@ def _real_extract(self, url):
fmt['acodec'] = 'aac' fmt['acodec'] = 'aac'
fmt['abr'] = 96 fmt['abr'] = 96
fmt['asr'] = 44100 fmt['asr'] = 44100
formats += [fmt] formats.append(fmt)
self._sort_formats(formats) self._sort_formats(formats)
# Get album art as thumbnails images = []
imgs = []
for name, info in track['images'].items(): for name, info in track['images'].items():
if name == 'dynamic' or info['url'] is None: image_url = info.get('url')
if name == 'dynamic' or not image_url:
continue continue
img = { img = {
'id': name, 'id': name,
'url': info['url'], 'url': image_url,
'height': info['height'], 'height': int_or_none(info.get('height')),
'width': info['width'], 'width': int_or_none(info.get('width')),
} }
imgs += [img] images.append(img)
return { return {
'id': track['id'], 'id': track['id'],
'display-id': track['slug'], 'display-id': track['slug'],
'title': title, 'title': title,
'formats': formats, 'formats': formats,
'thumbnails': imgs, 'thumbnails': images,
} }