diff options
| -rwxr-xr-x | youtube_dl/InfoExtractors.py | 57 | ||||
| -rw-r--r-- | youtube_dl/extractor/photobucket.py | 66 |
2 files changed, 67 insertions, 56 deletions
diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index b32bd3d94..d1488ade9 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -27,68 +27,13 @@ from .extractor.common import InfoExtractor, SearchInfoExtractor from .extractor.dailymotion import DailymotionIE from .extractor.metacafe import MetacafeIE from .extractor.statigram import StatigramIE +from .extractor.photobucket import PhotobucketIE from .extractor.youtube import YoutubeIE, YoutubePlaylistIE, YoutubeUserIE, YoutubeChannelIE -class PhotobucketIE(InfoExtractor): - """Information extractor for photobucket.com.""" - - # TODO: the original _VALID_URL was: - # r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)' - # Check if it's necessary to keep the old extracion process - _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*(([\?\&]current=)|_)(?P<id>.*)\.(?P<ext>(flv)|(mp4))' - IE_NAME = u'photobucket' - - def _real_extract(self, url): - # Extract id from URL - mobj = re.match(self._VALID_URL, url) - if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) - - video_id = mobj.group('id') - - video_extension = mobj.group('ext') - - # Retrieve video webpage to extract further information - webpage = self._download_webpage(url, video_id) - - # Extract URL, uploader, and title from webpage - self.report_extraction(video_id) - # We try first by looking the javascript code: - mobj = re.search(r'Pb\.Data\.Shared\.put\(Pb\.Data\.Shared\.MEDIA, (?P<json>.*?)\);', webpage) - if mobj is not None: - info = json.loads(mobj.group('json')) - return [{ - 'id': video_id, - 'url': info[u'downloadUrl'], - 'uploader': info[u'username'], - 'upload_date': datetime.date.fromtimestamp(info[u'creationDate']).strftime('%Y%m%d'), - 'title': info[u'title'], - 'ext': video_extension, - 'thumbnail': info[u'thumbUrl'], - }] - - # We try looking in other parts of the webpage - video_url = self._search_regex(r'<link rel="video_src" href=".*\?file=([^"]+)" />', - webpage, u'video URL') - - mobj = re.search(r'<title>(.*) video by (.*) - Photobucket</title>', webpage) - if mobj is None: - raise ExtractorError(u'Unable to extract title') - video_title = mobj.group(1).decode('utf-8') - video_uploader = mobj.group(2).decode('utf-8') - - return [{ - 'id': video_id.decode('utf-8'), - 'url': video_url.decode('utf-8'), - 'uploader': video_uploader, - 'upload_date': None, - 'title': video_title, - 'ext': video_extension.decode('utf-8'), - }] class YahooIE(InfoExtractor): diff --git a/youtube_dl/extractor/photobucket.py b/youtube_dl/extractor/photobucket.py new file mode 100644 index 000000000..cd7fe6f52 --- /dev/null +++ b/youtube_dl/extractor/photobucket.py @@ -0,0 +1,66 @@ +import datetime +import json +import re + +from .common import InfoExtractor + +from ..utils import ( + ExtractorError, +) + +class PhotobucketIE(InfoExtractor): + """Information extractor for photobucket.com.""" + + # TODO: the original _VALID_URL was: + # r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)' + # Check if it's necessary to keep the old extracion process + _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*(([\?\&]current=)|_)(?P<id>.*)\.(?P<ext>(flv)|(mp4))' + IE_NAME = u'photobucket' + + def _real_extract(self, url): + # Extract id from URL + mobj = re.match(self._VALID_URL, url) + if mobj is None: + raise ExtractorError(u'Invalid URL: %s' % url) + + video_id = mobj.group('id') + + video_extension = mobj.group('ext') + + # Retrieve video webpage to extract further information + webpage = self._download_webpage(url, video_id) + + # Extract URL, uploader, and title from webpage + self.report_extraction(video_id) + # We try first by looking the javascript code: + mobj = re.search(r'Pb\.Data\.Shared\.put\(Pb\.Data\.Shared\.MEDIA, (?P<json>.*?)\);', webpage) + if mobj is not None: + info = json.loads(mobj.group('json')) + return [{ + 'id': video_id, + 'url': info[u'downloadUrl'], + 'uploader': info[u'username'], + 'upload_date': datetime.date.fromtimestamp(info[u'creationDate']).strftime('%Y%m%d'), + 'title': info[u'title'], + 'ext': video_extension, + 'thumbnail': info[u'thumbUrl'], + }] + + # We try looking in other parts of the webpage + video_url = self._search_regex(r'<link rel="video_src" href=".*\?file=([^"]+)" />', + webpage, u'video URL') + + mobj = re.search(r'<title>(.*) video by (.*) - Photobucket</title>', webpage) + if mobj is None: + raise ExtractorError(u'Unable to extract title') + video_title = mobj.group(1).decode('utf-8') + video_uploader = mobj.group(2).decode('utf-8') + + return [{ + 'id': video_id.decode('utf-8'), + 'url': video_url.decode('utf-8'), + 'uploader': video_uploader, + 'upload_date': None, + 'title': video_title, + 'ext': video_extension.decode('utf-8'), + }] |