Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/hearthisat.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import (
   8     compat_urllib_request,
   9     compat_urlparse,
  10 )
  11 from ..utils import (
  12     HEADRequest,
  13     str_to_int,
  14     urlencode_postdata,
  15     urlhandle_detect_ext,
  16 )
  17
  18
  19 class HearThisAtIE(InfoExtractor):
  20     _VALID_URL = r'https?://(?:www\.)?hearthis\.at/(?P<artist>[^/]+)/(?P<title>[A-Za-z0-9\-]+)/?$'
  21     _PLAYLIST_URL = 'https://hearthis.at/playlist.php'
  22     _TEST = {
  23         'url': 'https://hearthis.at/moofi/dr-kreep',
  24         'md5': 'ab6ec33c8fed6556029337c7885eb4e0',
  25         'info_dict': {
  26             'id': '150939',
  27             'ext': 'wav',
  28             'title': 'Moofi - Dr. Kreep',
  29             'thumbnail': 're:^https?://.*\.jpg$',
  30             'timestamp': 1421564134,
  31             'description': 'Creepy Patch. Mutable Instruments Braids Vowel + Formant Mode.',
  32             'upload_date': '20150118',
  33             'comment_count': int,
  34             'view_count': int,
  35             'like_count': int,
  36             'duration': 71,
  37             'categories': ['Experimental'],
  38         }
  39     }
  40
  41     def _real_extract(self, url):
  42         m = re.match(self._VALID_URL, url)
  43         display_id = '{artist:s} - {title:s}'.format(**m.groupdict())
  44
  45         webpage = self._download_webpage(url, display_id)
  46         track_id = self._search_regex(
  47             r'intTrackId\s*=\s*(\d+)', webpage, 'track ID')
  48
  49         payload = urlencode_postdata({'tracks[]': track_id})
  50         req = compat_urllib_request.Request(self._PLAYLIST_URL, payload)
  51         req.add_header('Content-type', 'application/x-www-form-urlencoded')
  52
  53         track = self._download_json(req, track_id, 'Downloading playlist')[0]
  54         title = '{artist:s} - {title:s}'.format(**track)
  55
  56         categories = None
  57         if track.get('category'):
  58             categories = [track['category']]
  59
  60         description = self._og_search_description(webpage)
  61         thumbnail = self._og_search_thumbnail(webpage)
  62
  63         meta_span = r'<span[^>]+class="%s".*?</i>([^<]+)</span>'
  64         view_count = str_to_int(self._search_regex(
  65             meta_span % 'plays_count', webpage, 'view count', fatal=False))
  66         like_count = str_to_int(self._search_regex(
  67             meta_span % 'likes_count', webpage, 'like count', fatal=False))
  68         comment_count = str_to_int(self._search_regex(
  69             meta_span % 'comment_count', webpage, 'comment count', fatal=False))
  70         duration = str_to_int(self._search_regex(
  71             r'data-length="(\d+)', webpage, 'duration', fatal=False))
  72         timestamp = str_to_int(self._search_regex(
  73             r'<span[^>]+class="calctime"[^>]+data-time="(\d+)', webpage, 'timestamp', fatal=False))
  74
  75         formats = []
  76         mp3_url = self._search_regex(
  77             r'(?s)<a class="player-link"\s+(?:[a-zA-Z0-9_:-]+="[^"]+"\s+)*?data-mp3="([^"]+)"',
  78             webpage, 'mp3 URL', fatal=False)
  79         if mp3_url:
  80             formats.append({
  81                 'format_id': 'mp3',
  82                 'vcodec': 'none',
  83                 'acodec': 'mp3',
  84                 'url': mp3_url,
  85             })
  86         download_path = self._search_regex(
  87             r'<a class="[^"]*download_fct[^"]*"\s+href="([^"]+)"',
  88             webpage, 'download URL', default=None)
  89         if download_path:
  90             download_url = compat_urlparse.urljoin(url, download_path)
  91             ext_req = HEADRequest(download_url)
  92             ext_handle = self._request_webpage(
  93                 ext_req, display_id, note='Determining extension')
  94             ext = urlhandle_detect_ext(ext_handle)
  95             formats.append({
  96                 'format_id': 'download',
  97                 'vcodec': 'none',
  98                 'ext': ext,
  99                 'url': download_url,
 100                 'preference': 2,  # Usually better quality
 101             })
 102         self._sort_formats(formats)
 103
 104         return {
 105             'id': track_id,
 106             'display_id': display_id,
 107             'title': title,
 108             'formats': formats,
 109             'thumbnail': thumbnail,
 110             'description': description,
 111             'duration': duration,
 112             'timestamp': timestamp,
 113             'view_count': view_count,
 114             'comment_count': comment_count,
 115             'like_count': like_count,
 116             'categories': categories,
 117         }