diff options
author | Sergey M․ <dstftw@gmail.com> | 2014-12-26 23:16:25 +0600 |
---|---|---|
committer | Sergey M․ <dstftw@gmail.com> | 2014-12-26 23:16:25 +0600 |
commit | c2500434c3e63b0b5dff1d328d799907d9c1e418 (patch) | |
tree | 68d043637db3006be183fbbac6e95e9752027721 | |
parent | f74b341dde36fe2f56ab52c92416eb3ff5ccecf3 (diff) | |
parent | 461b00f34aabf6e75e0d53419919a8e6cc9cfd7a (diff) |
Merge branch 'eroprofile' of https://github.com/peugeot/youtube-dl into peugeot-eroprofile
-rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
-rw-r--r-- | youtube_dl/extractor/eroprofile.py | 53 |
2 files changed, 54 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index fd0ebffe3..39788712c 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -108,6 +108,7 @@ from .elpais import ElPaisIE from .empflix import EMPFlixIE from .engadget import EngadgetIE from .eporner import EpornerIE +from .eroprofile import EroProfileIE from .escapist import EscapistIE from .everyonesmixtape import EveryonesMixtapeIE from .exfm import ExfmIE diff --git a/youtube_dl/extractor/eroprofile.py b/youtube_dl/extractor/eroprofile.py new file mode 100644 index 000000000..f6745fc52 --- /dev/null +++ b/youtube_dl/extractor/eroprofile.py @@ -0,0 +1,53 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + +class EroProfileIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?eroprofile\.com/m/videos/view/(?P<display_id>[^/]+)' + _TEST = { + 'url': 'http://www.eroprofile.com/m/videos/view/sexy-babe-softcore', + 'md5': 'c26f351332edf23e1ea28ce9ec9de32f', + 'info_dict': { + 'id': '3733775', + 'ext': 'm4v', + 'title': 'HD MOVIES - sexy babe softcore', + 'description': 'md5:831ee50526c333eb4f6c1e58d382c295', + 'categories': list, # NSFW + 'thumbnail': 're:https?://.*\.jpg', + 'age_limit': 18, + } + } + + def _real_extract(self, url): + webpage = self._download_webpage(url, 'main') + + video_id = self._html_search_regex(r'glbUpdViews\s*\(\'\d*\',\'(\d+)\'', webpage, 'id') + + video_url = self._html_search_regex(r'<source src="([^"]+)', webpage, 'video_url') + + title = self._html_search_regex( + r'<title>([^<]+)\s*-\s*EroProfile</title>', webpage, 'title') + + description = self._html_search_meta('description', webpage, 'description', fatal=False) + + thumbnail = self._html_search_regex( + r'onclick="showVideoPlayer\(\)"><img src="([^"]+)', webpage, 'thumbnail', fatal=False) + + categories_str = self._html_search_meta( + 'keywords', webpage, 'categories', fatal=False) + categories = ( + None if categories_str is None + else categories_str.split(',')) + + return { + 'id': video_id, + 'url': video_url, + 'title': title, + 'ext': 'm4v', + 'description': description, + 'thumbnail': thumbnail, + 'categories': categories, + 'age_limit': 18, + } |