diff options
author | Sergey M. <[email protected]> | 2014-02-22 16:45:03 +0700 |
---|---|---|
committer | Sergey M. <[email protected]> | 2014-02-22 16:45:03 +0700 |
commit | 9767726b6689e25540530b6551296aed43a0808e (patch) | |
tree | 3b33020b2ded8b23ef75310f32c30cc71d321786 | |
parent | 1cf563d84baf84a208f4368b9b9f5b2e2b98ddd3 (diff) | |
download | youtube-dl-9767726b6689e25540530b6551296aed43a0808e.tar.gz youtube-dl-9767726b6689e25540530b6551296aed43a0808e.zip |
[spankwire] Improve and modernize
-rw-r--r-- | youtube_dl/extractor/spankwire.py | 65 |
1 files changed, 41 insertions, 24 deletions
diff --git a/youtube_dl/extractor/spankwire.py b/youtube_dl/extractor/spankwire.py index 3362b3db8..45703ec25 100644 --- a/youtube_dl/extractor/spankwire.py +++ b/youtube_dl/extractor/spankwire.py @@ -1,6 +1,5 @@ from __future__ import unicode_literals -import os import re from .common import InfoExtractor @@ -8,23 +7,27 @@ from ..utils import ( compat_urllib_parse_urlparse, compat_urllib_request, compat_urllib_parse, + unified_strdate, + str_to_int, + int_or_none, ) -from ..aes import ( - aes_decrypt_text -) +from ..aes import aes_decrypt_text class SpankwireIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>spankwire\.com/[^/]*/video(?P<videoid>[0-9]+)/?)' + _VALID_URL = r'https?://(?:www\.)?(?P<url>spankwire\.com/[^/]*/video(?P<videoid>[0-9]+)/?)' _TEST = { 'url': 'http://www.spankwire.com/Buckcherry-s-X-Rated-Music-Video-Crazy-Bitch/video103545/', - 'file': '103545.mp4', - 'md5': '1b3f55e345500552dbc252a3e9c1af43', + 'md5': '8bbfde12b101204b39e4b9fe7eb67095', 'info_dict': { - "uploader": "oreusz", - "title": "Buckcherry`s X Rated Music Video Crazy Bitch", - "description": "Crazy Bitch X rated music video.", - "age_limit": 18, + 'id': '103545', + 'ext': 'mp4', + 'title': 'Buckcherry`s X Rated Music Video Crazy Bitch', + 'description': 'Crazy Bitch X rated music video.', + 'uploader': 'oreusz', + 'uploader_id': '124697', + 'upload_date': '20070508', + 'age_limit': 18, } } @@ -37,13 +40,26 @@ class SpankwireIE(InfoExtractor): req.add_header('Cookie', 'age_verified=1') webpage = self._download_webpage(req, video_id) - video_title = self._html_search_regex(r'<h1>([^<]+)', webpage, 'title') - video_uploader = self._html_search_regex( - r'by:\s*<a [^>]*>(.+?)</a>', webpage, 'uploader', fatal=False) - thumbnail = self._html_search_regex( - r'flashvars\.image_url = "([^"]+)', webpage, 'thumbnail', fatal=False) + title = self._html_search_regex(r'<h1>([^<]+)', webpage, 'title') description = self._html_search_regex( r'<div\s+id="descriptionContent">([^<]+)<', webpage, 'description', fatal=False) + thumbnail = self._html_search_regex( + r'flashvars\.image_url = "([^"]+)', webpage, 'thumbnail', fatal=False) + + uploader = self._html_search_regex( + r'by:\s*<a [^>]*>(.+?)</a>', webpage, 'uploader', fatal=False) + uploader_id = self._html_search_regex( + r'by:\s*<a href="/Profile.aspx?.*?UserId=(\d+).*?"', webpage, 'uploader id', fatal=False) + upload_date = self._html_search_regex(r'</a> on (.+?) at \d+:\d+', webpage, 'upload date', fatal=False) + if upload_date: + upload_date = unified_strdate(upload_date) + + view_count = self._html_search_regex( + r'<div id="viewsCounter"><span>([^<]+)</span> views</div>', webpage, 'view count', fatal=False) + if view_count: + view_count = str_to_int(view_count) + comment_count = int_or_none(self._html_search_regex( + r'<span id="spCommentCount">\s*(\d+)</span> Comments</div>', webpage, 'comment count', fatal=False)) video_urls = list(map(compat_urllib_parse.unquote , re.findall(r'flashvars\.quality_[0-9]{3}p = "([^"]+)', webpage))) if webpage.find('flashvars\.encrypted = "true"') != -1: @@ -53,16 +69,13 @@ class SpankwireIE(InfoExtractor): formats = [] for video_url in video_urls: path = compat_urllib_parse_urlparse(video_url).path - extension = os.path.splitext(path)[1][1:] format = path.split('/')[4].split('_')[:2] resolution, bitrate_str = format format = "-".join(format) - height = int(resolution.rstrip('P')) - tbr = int(bitrate_str.rstrip('K')) - + height = int(resolution.rstrip('Pp')) + tbr = int(bitrate_str.rstrip('Kk')) formats.append({ 'url': video_url, - 'ext': extension, 'resolution': resolution, 'format': format, 'tbr': tbr, @@ -75,10 +88,14 @@ class SpankwireIE(InfoExtractor): return { 'id': video_id, - 'uploader': video_uploader, - 'title': video_title, - 'thumbnail': thumbnail, + 'title': title, 'description': description, + 'thumbnail': thumbnail, + 'uploader': uploader, + 'uploader_id': uploader_id, + 'upload_date': upload_date, + 'view_count': view_count, + 'comment_count': comment_count, 'formats': formats, 'age_limit': age_limit, } |