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

Fix flask8 issues. Ready to pull

Browse Source
This commit is contained in:
Allan Daemon 2017-05-18 04:16:38 -03:00
parent 6a84bb616c
commit 586fd077de
1 changed files with 46 additions and 62 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
youtube_dl/extractor/palcomp3.py
View File

@ -3,12 +3,9 @@ from __future__ import unicode_literals
import re
from ..compat import compat_etree_fromstring
from ..utils import get_element_by_id, get_element_by_attribute
from .common import InfoExtractor
# TEMP FOR DEV
from pprint import pprint as pp
class PalcoMP3IE(InfoExtractor):
IE_NAME = 'PalcoMP3:song'
@ -41,15 +38,13 @@ class PalcoMP3IE(InfoExtractor):
`_json_ld` function does not fit us."""
return self._parse_json(json_ld, display_id, fatal=fatal)
def _extract_common(self, url):
artist_id = self._VALID_URL_RE.match(url).group('artist')
webpage = self._download_webpage(url, artist_id)
print ("Webpage", type(webpage), len(webpage))
self.webpage = webpage
ld = self._get_ld_info(webpage, artist_id)
tracks = [ self._ld_track_process(track, ld) for track in ld['track'] ]
tracks = [self._ld_track_process(track, ld) for track in ld['track']]
return tracks, ld, webpage
@ -63,19 +58,13 @@ class PalcoMP3IE(InfoExtractor):
else:
return track
def _get_ld_info(self, webpage, display_id):
# player = get_element_by_attribute('id', 'player', webpage, escape_value=False)
player = get_element_by_id('player', webpage)
pp(player)
player = get_element_by_id('player', webpage) or \
get_element_by_attribute('id', 'player', webpage, escape_value=False)
ld = self._search_json_ld(player, display_id, expected_type="MusicGroup")
print("LD:")
pp(ld)
return ld
def _ld_track_process(self, track, ld={'genre':None}):
def _ld_track_process(self, track, ld={'genre': None}):
tmin, tsec = re.findall("PT(\d+)M(\d+)S", track['duration'], re.IGNORECASE)[0]
return {
@ -87,7 +76,7 @@ class PalcoMP3IE(InfoExtractor):
'artist': track['byArtist']['name'],
'thumbnail': track['byArtist']['image'],
'display_id': track['url'].split('/')[-2],
'duration': int(tmin)*60 + int(tsec),
'duration': int(tmin) * 60 + int(tsec),
'genre': ld['genre'],
}
@ -113,14 +102,14 @@ class PalcoMP3ArtistIE(PalcoMP3IE):
'playlist_count': 4,
},
# Active famous artist; Very likely to change the playlist a lot
# Active famous artist; Very likely to change playlist_count.
# {
# 'url': 'https://www.palcomp3.com/maiaraemaraisaoficial',
# 'info_dict': {
# 'id': 'maiaraemaraisaoficial',
# 'title': 'Maiara e Maraisa Oficial',
# },
# 'playlist_count': '>8',
# 'playlist_count': 8,
# },
]
@ -144,7 +133,8 @@ class PalcoMP3VideoIE(PalcoMP3IE):
'upload_date': '20161107',
'uploader_id': 'maiaramaraisaoficial',
'uploader': 'Maiara e Maraisa',
}},
}
},
{
'url': 'https://www.palcomp3.com/mckevinho/dog-vagabundo-mc-phe-cachorrera-part-mc-kevinho/#clipe',
'add_ie': ['Youtube'],
@ -156,13 +146,12 @@ class PalcoMP3VideoIE(PalcoMP3IE):
'upload_date': '20170208',
'uploader': 'GR6 EXPLODE',
'uploader_id': 'gr6explode',
}},
}
},
]
def _real_extract(self, url):
track, webpage = super(PalcoMP3VideoIE, self)._real_extract(url, with_webpage=True)
print "TRACK"
pp(track)
video_re = r"""
(?x)
@ -174,13 +163,8 @@ class PalcoMP3VideoIE(PalcoMP3IE):
""".format(track['id'])
m = re.search(video_re, webpage)
# from IPython import embed
# embed()
if not m:
return None
video_id = m.group('video_id')
return {