fenix
/
yt-dlp
mirror of https://github.com/yt-dlp/yt-dlp.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

[novamov] Generalize extractor

This commit is contained in:
Sergey M. 2014-02-24 23:30:09 +07:00
parent d6f0d86649
commit ce78943ae1
2 changed files with 25 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
youtube_dl/extractor/__init__.py
View File

@ -161,7 +161,7 @@ from .nhl import NHLIE, NHLVideocenterIE
from .niconico import NiconicoIE from .niconico import NiconicoIE
from .ninegag import NineGagIE from .ninegag import NineGagIE
from .normalboots import NormalbootsIE from .normalboots import NormalbootsIE
from .novamov import NovamovIE from .novamov import NovaMovIE
from .nowness import NownessIE from .nowness import NownessIE
from .nowvideo import NowVideoIE from .nowvideo import NowVideoIE
from .ooyala import OoyalaIE from .ooyala import OoyalaIE

40
youtube_dl/extractor/novamov.py
View File

@ -9,14 +9,25 @@ from ..utils import (
) )
class NovamovIE(InfoExtractor): class NovaMovIE(InfoExtractor):
_VALID_URL = r'http://(?:(?:www\.)?novamov\.com/video/|(?:(?:embed|www)\.)novamov\.com/embed\.php\?(?:.*?&)?v=)(?P<videoid>[a-z\d]{13})' IE_NAME = 'novamov'
IE_DESC = 'NovaMov'
_VALID_URL = r'http://(?:(?:www\.)?%(host)s/video/|(?:(?:embed|www)\.)%(host)s/embed\.php\?(?:.*?&)?v=)(?P<videoid>[a-z\d]{13})' % {'host': 'novamov\.com'}
_HOST = 'www.novamov.com'
_FILE_DELETED_REGEX = r'This file no longer exists on our servers!</h2>'
_FILEKEY_REGEX = r'flashvars\.filekey="(?P<filekey>[^"]+)";'
_TITLE_REGEX = r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>([^<]+)</h3>'
_DESCRIPTION_REGEX = r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>[^<]+</h3><p>([^<]+)</p>'
_TEST = { _TEST = {
'url': 'http://www.novamov.com/video/4rurhn9x446jj', 'url': 'http://www.novamov.com/video/4rurhn9x446jj',
'file': '4rurhn9x446jj.flv',
'md5': '7205f346a52bbeba427603ba10d4b935', 'md5': '7205f346a52bbeba427603ba10d4b935',
'info_dict': { 'info_dict': {
'id': '4rurhn9x446jj',
'ext': 'flv',
'title': 'search engine optimization', 'title': 'search engine optimization',
'description': 'search engine optimization is used to rank the web page in the google search engine' 'description': 'search engine optimization is used to rank the web page in the google search engine'
}, },
@ -27,31 +38,26 @@ class NovamovIE(InfoExtractor):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('videoid') video_id = mobj.group('videoid')
page = self._download_webpage('http://www.novamov.com/video/%s' % video_id, page = self._download_webpage(
video_id, 'Downloading video page') 'http://%s/video/%s' % (self._HOST, video_id), video_id, 'Downloading video page')
if re.search(r'This file no longer exists on our servers!</h2>', page) is not None: if re.search(self._FILE_DELETED_REGEX, page) is not None:
raise ExtractorError(u'Video %s does not exist' % video_id, expected=True) raise ExtractorError(u'Video %s does not exist' % video_id, expected=True)
filekey = self._search_regex( filekey = self._search_regex(self._FILEKEY_REGEX, page, 'filekey')
r'flashvars\.filekey="(?P<filekey>[^"]+)";', page, 'filekey')
title = self._html_search_regex( title = self._html_search_regex(self._TITLE_REGEX, page, 'title', fatal=False)
r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>([^<]+)</h3>',
page, 'title', fatal=False)
description = self._html_search_regex( description = self._html_search_regex(self._DESCRIPTION_REGEX, page, 'description', default='', fatal=False)
r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>[^<]+</h3><p>([^<]+)</p>',
page, 'description', fatal=False)
api_response = self._download_webpage( api_response = self._download_webpage(
'http://www.novamov.com/api/player.api.php?key=%s&file=%s' % (filekey, video_id), 'http://%s/api/player.api.php?key=%s&file=%s' % (self._HOST, filekey, video_id), video_id,
video_id, 'Downloading video api response') 'Downloading video api response')
response = compat_urlparse.parse_qs(api_response) response = compat_urlparse.parse_qs(api_response)
if 'error_msg' in response: if 'error_msg' in response:
raise ExtractorError('novamov returned error: %s' % response['error_msg'][0], expected=True) raise ExtractorError('%s returned error: %s' % (self.IE_NAME, response['error_msg'][0]), expected=True)
video_url = response['url'][0] video_url = response['url'][0]