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

32
youtube_dl/extractor/palcomp3.py
View File

@ -3,12 +3,9 @@ from __future__ import unicode_literals
import re import re
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
# TEMP FOR DEV
from pprint import pprint as pp
class PalcoMP3IE(InfoExtractor): class PalcoMP3IE(InfoExtractor):
IE_NAME = 'PalcoMP3:song' IE_NAME = 'PalcoMP3:song'
@ -41,11 +38,9 @@ class PalcoMP3IE(InfoExtractor):
`_json_ld` function does not fit us.""" `_json_ld` function does not fit us."""
return self._parse_json(json_ld, display_id, fatal=fatal) return self._parse_json(json_ld, display_id, fatal=fatal)
def _extract_common(self, url): def _extract_common(self, url):
artist_id = self._VALID_URL_RE.match(url).group('artist') artist_id = self._VALID_URL_RE.match(url).group('artist')
webpage = self._download_webpage(url, artist_id) webpage = self._download_webpage(url, artist_id)
print ("Webpage", type(webpage), len(webpage))
self.webpage = webpage self.webpage = webpage
ld = self._get_ld_info(webpage, artist_id) ld = self._get_ld_info(webpage, artist_id)
@ -63,16 +58,10 @@ class PalcoMP3IE(InfoExtractor):
else: else:
return track return track
def _get_ld_info(self, webpage, display_id): 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) or \
player = get_element_by_id('player', webpage) get_element_by_attribute('id', 'player', webpage, escape_value=False)
pp(player)
ld = self._search_json_ld(player, display_id, expected_type="MusicGroup") ld = self._search_json_ld(player, display_id, expected_type="MusicGroup")
print("LD:")
pp(ld)
return ld return ld
def _ld_track_process(self, track, ld={'genre': None}): def _ld_track_process(self, track, ld={'genre': None}):
@ -113,14 +102,14 @@ class PalcoMP3ArtistIE(PalcoMP3IE):
'playlist_count': 4, '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', # 'url': 'https://www.palcomp3.com/maiaraemaraisaoficial',
# 'info_dict': { # 'info_dict': {
# 'id': 'maiaraemaraisaoficial', # 'id': 'maiaraemaraisaoficial',
# 'title': 'Maiara e Maraisa Oficial', # 'title': 'Maiara e Maraisa Oficial',
# }, # },
# 'playlist_count': '>8', # 'playlist_count': 8,
# }, # },
] ]
@ -144,7 +133,8 @@ class PalcoMP3VideoIE(PalcoMP3IE):
'upload_date': '20161107', 'upload_date': '20161107',
'uploader_id': 'maiaramaraisaoficial', 'uploader_id': 'maiaramaraisaoficial',
'uploader': 'Maiara e Maraisa', 'uploader': 'Maiara e Maraisa',
}}, }
},
{ {
'url': 'https://www.palcomp3.com/mckevinho/dog-vagabundo-mc-phe-cachorrera-part-mc-kevinho/#clipe', 'url': 'https://www.palcomp3.com/mckevinho/dog-vagabundo-mc-phe-cachorrera-part-mc-kevinho/#clipe',
'add_ie': ['Youtube'], 'add_ie': ['Youtube'],
@ -156,13 +146,12 @@ class PalcoMP3VideoIE(PalcoMP3IE):
'upload_date': '20170208', 'upload_date': '20170208',
'uploader': 'GR6 EXPLODE', 'uploader': 'GR6 EXPLODE',
'uploader_id': 'gr6explode', 'uploader_id': 'gr6explode',
}}, }
},
] ]
def _real_extract(self, url): def _real_extract(self, url):
track, webpage = super(PalcoMP3VideoIE, self)._real_extract(url, with_webpage=True) track, webpage = super(PalcoMP3VideoIE, self)._real_extract(url, with_webpage=True)
print "TRACK"
pp(track)
video_re = r""" video_re = r"""
(?x) (?x)
@ -174,13 +163,8 @@ class PalcoMP3VideoIE(PalcoMP3IE):
""".format(track['id']) """.format(track['id'])
m = re.search(video_re, webpage) m = re.search(video_re, webpage)
# from IPython import embed
# embed()
if not m: if not m:
return None return None
video_id = m.group('video_id') video_id = m.group('video_id')
return { return {