diff options
| -rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
| -rw-r--r-- | youtube_dl/extractor/normalboots.py | 50 |
2 files changed, 51 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index e89b5cf9d..663c8bd7f 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -141,6 +141,7 @@ from .newgrounds import NewgroundsIE from .nhl import NHLIE, NHLVideocenterIE from .niconico import NiconicoIE from .ninegag import NineGagIE +from .normalboots import NormalbootsIE from .novamov import NovamovIE from .nowness import NownessIE from .nowvideo import NowVideoIE diff --git a/youtube_dl/extractor/normalboots.py b/youtube_dl/extractor/normalboots.py new file mode 100644 index 000000000..75a5fa0a6 --- /dev/null +++ b/youtube_dl/extractor/normalboots.py @@ -0,0 +1,50 @@ +import re + +from .common import InfoExtractor + +from ..utils import ( + ExtractorError, + unified_strdate, +) + +class NormalbootsIE(InfoExtractor): + _VALID_URL = r'(?:http://)?(?:www\.)?normalboots\.com/video/(?P<videoid>[0-9a-z-]*)/?$' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + raise ExtractorError(u'Invalid URL: %s' % url) + video_id = mobj.group('videoid') + + info = { + 'id': video_id, + 'uploader': None, + 'upload_date': None, + } + + if url[:4] != 'http': + url = 'http://' + url + + webpage = self._download_webpage(url, video_id) + video_title = self._og_search_title(webpage) + video_description = self._og_search_description(webpage) + video_thumbnail = self._og_search_thumbnail(webpage) + video_uploader = self._html_search_regex(r'Posted\sby\s<a\shref="[A-Za-z0-9/]*">(?P<uploader>[A-Za-z]*)\s</a>', + webpage, 'uploader') + raw_upload_date = self._html_search_regex('<span style="text-transform:uppercase; font-size:inherit;">[A-Za-z]+, (?P<date>.*)</span>', + webpage, 'date') + video_upload_date = unified_strdate(raw_upload_date) + video_upload_date = unified_strdate(raw_upload_date) + + player_url = self._html_search_regex(r'<iframe\swidth="[0-9]+"\sheight="[0-9]+"\ssrc="(?P<url>[\S]+)"', webpage, 'url') + player_page = self._download_webpage(player_url, video_id) + video_url = u'http://player.screenwavemedia.com/' + self._html_search_regex(r"'file':\s'(?P<file>[0-9A-Za-z-_\.]+)'", player_page, 'file') + + info['url'] = video_url + info['title'] = video_title + info['description'] = video_description + info['thumbnail'] = video_thumbnail + info['uploader'] = video_uploader + info['upload_date'] = video_upload_date + + return info |