diff options
author | Mister Hat <misterhat144@gmail.com> | 2015-05-24 15:26:59 -0500 |
---|---|---|
committer | Mister Hat <misterhat144@gmail.com> | 2015-05-24 15:26:59 -0500 |
commit | 7198063d96003050eccb0ea59cc938f0388c0606 (patch) | |
tree | 6e86d96f5cacb57981cee3ec2d501589220a3e9c /youtube_dl/extractor | |
parent | d41ebe146b693011eb1020ca9cd935e7db892d0b (diff) |
[pinkbike] new extractor
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
-rw-r--r-- | youtube_dl/extractor/pinkbike.py | 78 |
2 files changed, 79 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 79bcd9106..80bec39da 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -394,6 +394,7 @@ from .pbs import PBSIE from .philharmoniedeparis import PhilharmonieDeParisIE from .phoenix import PhoenixIE from .photobucket import PhotobucketIE +from .pinkbike import PinkbikeIE from .planetaplay import PlanetaPlayIE from .pladform import PladformIE from .played import PlayedIE diff --git a/youtube_dl/extractor/pinkbike.py b/youtube_dl/extractor/pinkbike.py new file mode 100644 index 000000000..4a15c1835 --- /dev/null +++ b/youtube_dl/extractor/pinkbike.py @@ -0,0 +1,78 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class PinkbikeIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?pinkbike\.com/video/(?P<id>[0-9]+)' + _TESTS = [{ + 'url': 'http://www.pinkbike.com/video/402811/', + 'md5': '4814b8ca7651034cd87e3361d5c2155a', + 'info_dict': { + 'id': '402811', + 'ext': 'mp4', + 'title': 'Brandon Semenuk - RAW 100', + 'thumbnail': 're:^https?://.*\.jpg$', + 'location': 'Victoria, British Columbia, Canada', + 'uploader_id': 'revelco', + 'upload_date': '20150406', + 'description': 'Official release: www.redbull.ca/rupertwalker', + 'duration': '100' + } + }, { + 'url': 'http://www.pinkbike.com/video/406629/', + 'md5': 'c7a3e19a2bd5cde5a1cda6b2b46caa74', + 'info_dict': { + 'id': '406629', + 'ext': 'mp4', + 'title': 'Chromag: Reece Wallace in Utah', + 'thumbnail': 're:^https?://.*\.jpg$', + 'location': 'Whistler, British Columbia, Canada', + 'uploader_id': 'Chromagbikes', + 'upload_date': '20150505', + 'description': 'Reece Wallace shredding Virgin, Utah. Video by Virtu Media.', + 'duration': '180' + } + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title') + title = title[:-len(' Video - Pinkbike')] + + description = self._html_search_meta('description', webpage, 'description') + description = description[len(title + '. '):] + + uploader_id = self._html_search_regex(r'un:\s*"(.*?)"', webpage, 'uploader_id') + + upload_date = self._html_search_regex( + r'class="fullTime"\s*title="([0-9]{4}(?:-[0-9]{2}){2})"', + webpage, 'upload_date') + upload_date = upload_date.replace('-', '') + + location = self._html_search_regex( + r'<dt>Location</dt>\n?\s*<dd>\n?(.*?)\s*<img', + webpage, 'location') + + formats = re.findall( + r'<source data-quality=\\"([0-9]+)p\\" src=\\"(.*?)\\">', + webpage) + + formats = [{'url': fmt[1], 'height': fmt[0]} for fmt in formats] + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'duration': self._html_search_meta('video:duration', webpage, 'duration'), + 'thumbnail': self._html_search_meta('og:image', webpage, 'thumbnail'), + 'uploader_id': uploader_id, + 'upload_date': upload_date, + 'location': location, + 'formats': formats + } |