R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

PalcoMP3: Getting song fine

Browse Source
This commit is contained in:
Allan Daemon 2017-05-15 02:37:11 -03:00
parent 4cf35c4bdb
commit 2c7edaf8f6
1 changed files with 49 additions and 35 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

84
youtube_dl/extractor/palcomp3.py
View File

@ -1,6 +1,8 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from ..compat import compat_etree_fromstring from ..compat import compat_etree_fromstring
from ..utils import get_element_by_id, get_element_by_attribute from ..utils import get_element_by_id, get_element_by_attribute
from .common import InfoExtractor from .common import InfoExtractor
@ -10,60 +12,72 @@ from pprint import pprint as pp
class PalcoMP3IE(InfoExtractor): class PalcoMP3IE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?palcomp3\.com/(?P<artist>[^/]+)/(?P<id>[^/]+)' _VALID_URL = r'https?://(?:www\.)?palcomp3\.com/(?P<artist>[^/]+)/(?P<id>[^/]+)'
_TEST = { _TESTS = [{
'url': 'https://www.palcomp3.com/maiaraemaraisaoficial/nossas-composicoes-cuida-bem-dela/', 'url': 'https://www.palcomp3.com/maiaraemaraisaoficial/nossas-composicoes-cuida-bem-dela/',
'md5': '0effca14d6640568df0c1daa1e5609e2', 'md5': '99fd6405b2d8fd589670f6db1ba3b358',
'info_dict': { 'info_dict': {
'id': 'nossas-composicoes-cuida-bem-dela', 'id': '3162927',
'ext': 'mp3', 'ext': 'mp3',
'display_id': 'nossas-composicoes-cuida-bem-dela',
'title': 'Nossas Composições - CUIDA BEM DELA', 'title': 'Nossas Composições - CUIDA BEM DELA',
'thumbnail': r'https://studiosol-a.akamaihd.net/tb/468x351/palcomp3-logo/9/d/f/c/356447_20170324175145.jpg', 'thumbnail': r'https://studiosol-a.akamaihd.net/tb/80x60/palcomp3-logo/9/d/f/c/356447_20170324175145.jpg',
# TODO more properties, either as: }},
# * A value {
# * MD5 checksum; start the string with md5: 'url': 'https://www.palcomp3.com/maiaraemaraisaoficial/niveis-da-bebida/',
# * A regular expression; start the string with re: 'md5': '4c4d1e45b5ae49396cfff017eb41cdd9',
# * Any Python type (for example int or float) 'info_dict': {
} 'id': '2303899',
} 'ext': 'mp3',
'display_id': 'niveis-da-bebida',
'title': 'NIVEIS DA BEBIDA',
'thumbnail': r'https://studiosol-a.akamaihd.net/tb/80x60/palcomp3-logo/9/d/f/c/356447_20170324175145.jpg',
}},
]
def _json_ld(self, json_ld, video_id, fatal=True, expected_type="MusicGroup"): def _json_ld(self, json_ld, display_id, fatal=True, expected_type="MusicGroup"):
""" override `common.py:_json_ld` as we just need the """ override `common.py:_json_ld` as we just need the
`_search_json_ld` function to get the JSON, but the original `_search_json_ld` function to get the JSON, but the original
`_json_ld` function does not fit us.""" `_json_ld` function does not fit us."""
return self._parse_json(json_ld, video_id, fatal=fatal) return self._parse_json(json_ld, display_id, fatal=fatal)
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) display_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, display_id)
print ("Webpage", type(webpage), len(webpage)) print ("Webpage", type(webpage), len(webpage))
ld = self._get_ld_info(webpage, display_id)
tracks = [ self._ld_track_process(track, ld) for track in ld['track'] ]
# from IPython import embed
# embed()
for track in tracks:
if track['display_id'] == display_id:
return track
player = get_element_by_id('player', webpage)
def _get_ld_info(self, webpage, display_id):
# player = get_element_by_attribute('id', 'player', webpage, escape_value=False) # player = get_element_by_attribute('id', 'player', webpage, escape_value=False)
player = get_element_by_id('player', webpage)
pp(player) pp(player)
ld = self._search_json_ld(player, display_id, expected_type="MusicGroup")
ld = self._search_json_ld(player, video_id, expected_type="MusicGroup")
print("LD:") print("LD:")
pp(ld) pp(ld)
# from IPython import embed return ld
# embed()
info = self._ld_track_process(ld['track'][0]) def _ld_track_process(self, track, ld={'genre':None}):
tmin, tsec = re.findall("PT(\d+)M(\d+)S", track['duration'], re.IGNORECASE)[0]
return { return {
'id': video_id, 'id': track['@id'],
'title': self._og_search_title(webpage), 'title': track['name'],
'thumbnail': self._og_search_thumbnail(webpage), 'track': track['name'],
# 'description': self._og_search_description(webpage), 'url': 'https:' + track['audio'],
# 'uploader': self._search_regex(r'<div[^>]+id="uploader"[^>]*>([^<]+)<', webpage, 'uploader', fatal=False), 'webpage_url': 'https://www.palcomp3.com' + track['url'],
# TODO more properties (see youtube_dl/extractor/common.py) 'artist': track['byArtist']['name'],
'url': 'https:' + ld['track'][0]['audio'], 'thumbnail': track['byArtist']['image'],
} 'display_id': track['url'].split('/')[-2],
'duration': int(tmin)*60 + int(tsec),
'genre': ld['genre'],
def _ld_track_process(self, track):
return {
'url': 'https:' + track['audio']
} }