1
0
mirror of https://github.com/l1ving/youtube-dl synced 2024-12-31 01:52:52 +08:00

[hypem] Move into own file

This commit is contained in:
Philipp Hagemeister 2013-06-23 22:29:27 +02:00
parent 9fe4de3471
commit 27110b0567
2 changed files with 64 additions and 48 deletions

View File

@ -34,6 +34,7 @@ from .extractor.gametrailers import GametrailersIE
from .extractor.generic import GenericIE
from .extractor.googleplus import GooglePlusIE
from .extractor.googlesearch import GoogleSearchIE
from .extractor.hypem import HypemIE
from .extractor.ina import InaIE
from .extractor.infoq import InfoQIE
from .extractor.justintv import JustinTVIE
@ -280,55 +281,7 @@ class XHamsterIE(InfoExtractor):
'thumbnail': video_thumbnail
}]
class HypemIE(InfoExtractor):
"""Information Extractor for hypem"""
_VALID_URL = r'(?:http://)?(?:www\.)?hypem\.com/track/([^/]+)/([^/]+)'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
track_id = mobj.group(1)
data = { 'ax': 1, 'ts': time.time() }
data_encoded = compat_urllib_parse.urlencode(data)
complete_url = url + "?" + data_encoded
request = compat_urllib_request.Request(complete_url)
response, urlh = self._download_webpage_handle(request, track_id, u'Downloading webpage with the url')
cookie = urlh.headers.get('Set-Cookie', '')
self.report_extraction(track_id)
html_tracks = self._html_search_regex(r'<script type="application/json" id="displayList-data">(.*?)</script>',
response, u'tracks', flags=re.MULTILINE|re.DOTALL).strip()
try:
track_list = json.loads(html_tracks)
track = track_list[u'tracks'][0]
except ValueError:
raise ExtractorError(u'Hypemachine contained invalid JSON.')
key = track[u"key"]
track_id = track[u"id"]
artist = track[u"artist"]
title = track[u"song"]
serve_url = "http://hypem.com/serve/source/%s/%s" % (compat_str(track_id), compat_str(key))
request = compat_urllib_request.Request(serve_url, "" , {'Content-Type': 'application/json'})
request.add_header('cookie', cookie)
song_data_json = self._download_webpage(request, track_id, u'Downloading metadata')
try:
song_data = json.loads(song_data_json)
except ValueError:
raise ExtractorError(u'Hypemachine contained invalid JSON.')
final_url = song_data[u"url"]
return [{
'id': track_id,
'url': final_url,
'ext': "mp3",
'title': title,
'artist': artist,
}]

View File

@ -0,0 +1,63 @@
import json
import re
import time
from .common import InfoExtractor
from ..utils import (
compat_str,
compat_urllib_parse,
compat_urllib_request,
ExtractorError,
)
class HypemIE(InfoExtractor):
"""Information Extractor for hypem"""
_VALID_URL = r'(?:http://)?(?:www\.)?hypem\.com/track/([^/]+)/([^/]+)'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
track_id = mobj.group(1)
data = { 'ax': 1, 'ts': time.time() }
data_encoded = compat_urllib_parse.urlencode(data)
complete_url = url + "?" + data_encoded
request = compat_urllib_request.Request(complete_url)
response, urlh = self._download_webpage_handle(request, track_id, u'Downloading webpage with the url')
cookie = urlh.headers.get('Set-Cookie', '')
self.report_extraction(track_id)
html_tracks = self._html_search_regex(r'<script type="application/json" id="displayList-data">(.*?)</script>',
response, u'tracks', flags=re.MULTILINE|re.DOTALL).strip()
try:
track_list = json.loads(html_tracks)
track = track_list[u'tracks'][0]
except ValueError:
raise ExtractorError(u'Hypemachine contained invalid JSON.')
key = track[u"key"]
track_id = track[u"id"]
artist = track[u"artist"]
title = track[u"song"]
serve_url = "http://hypem.com/serve/source/%s/%s" % (compat_str(track_id), compat_str(key))
request = compat_urllib_request.Request(serve_url, "" , {'Content-Type': 'application/json'})
request.add_header('cookie', cookie)
song_data_json = self._download_webpage(request, track_id, u'Downloading metadata')
try:
song_data = json.loads(song_data_json)
except ValueError:
raise ExtractorError(u'Hypemachine contained invalid JSON.')
final_url = song_data[u"url"]
return [{
'id': track_id,
'url': final_url,
'ext': "mp3",
'title': title,
'artist': artist,
}]