From 4ea3137e41e17fc29b29541990162fca877df7b4 Mon Sep 17 00:00:00 2001 From: MikeCol Date: Mon, 10 Mar 2014 14:41:19 +0100 Subject: [PATCH] Playvid extractor --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/playvid.py | 85 ++++++++++++++++++++++++++++++++ 2 files changed, 86 insertions(+) create mode 100644 youtube_dl/extractor/playvid.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index d43e6b764..4a14a2be6 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -176,6 +176,7 @@ from .ooyala import OoyalaIE from .orf import ORFIE from .pbs import PBSIE from .photobucket import PhotobucketIE +from .playvid import PlayvidIE from .podomatic import PodomaticIE from .pornhd import PornHdIE from .pornhub import PornHubIE diff --git a/youtube_dl/extractor/playvid.py b/youtube_dl/extractor/playvid.py new file mode 100644 index 000000000..a74f8f675 --- /dev/null +++ b/youtube_dl/extractor/playvid.py @@ -0,0 +1,85 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_parse, + determine_ext, +) + +class PlayvidIE(InfoExtractor): + + _VALID_URL = r'^(?:https?://)?www\.playvid\.com/watch(\?v=|/)(?P.+?)(#|$)' + _TEST = { + 'url': 'http://www.playvid.com/watch/agbDDi7WZTV', + 'file': 'agbDDi7WZTV.mp4', + 'md5': '44930f8afa616efdf9482daf4fe53e1e', + 'info_dict': { + 'title': 'Michelle Lewin in Miami Beach', + 'duration': 240, + 'age_limit': 18, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + self.report_extraction(video_id) + + video_title = None + duration = None + video_thumbnail = None + formats = [] + + # most of the information is stored in the flashvars + flashvars_match = re.search(r'flashvars="(.+?)"',webpage) + + if flashvars_match: + infos = compat_urllib_parse.unquote(flashvars_match.group(1)).split(r'&') + for info in infos: + videovars_match = re.match(r'^video_vars\[(.+?)\]=(.+?)$',info) + if videovars_match: + key = videovars_match.group(1) + val = videovars_match.group(2) + + if key == 'title': + video_title = val.replace('+',' ') + if key == 'duration': + try: + duration = val + except ValueError: + duration = None + if key == 'big_thumb': + video_thumbnail = val + + videourl_match = re.match(r'^video_urls\]\[(?P\d+)p',key) + if videourl_match: + resolution = int(videourl_match.group('resolution')) + formats.append({ + 'resolution': resolution, # 360, 480, ... + 'ext': determine_ext(val), + 'url': val + }) + + # fatal error, if no download url is found + if len(formats) == 0: + raise ExtractorError,'no video url found' + + # Extract title - should be in the flashvars; if not, look elsewhere + if video_title is None: + video_title = self._html_search_regex( + r'(.*?)</title', webpage, 'title') + + return { + 'id': video_id, + 'formats': formats, + 'title': video_title, + 'thumbnail': video_thumbnail, + 'duration': duration, + 'description': None, + 'age_limit': 18 + } -- 2.22.2