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