youtube-dl/youtube_dl/extractor/googledrive.py

130 lines
4.2 KiB
Python
Raw Normal View History

2015-06-29 06:53:21 +00:00
import re
2015-06-24 00:13:23 +00:00
from .common import InfoExtractor
from ..utils import RegexNotFoundError
2015-06-29 06:53:21 +00:00
class GoogleDriveEmbedIE(InfoExtractor):
2015-07-17 13:17:19 +00:00
_VALID_URL = r'https?://(?:video\.google\.com/get_player\?.*?docid=|(?:docs|drive)\.google\.com/file/d/)(?P<id>[a-zA-Z0-9_-]{28})'
2015-06-29 06:53:21 +00:00
_TEST = {
'url': 'https://docs.google.com/file/d/0B8KB9DRosYGKMXNoeWxqa3JYclE/preview',
'info_dict': {
'id': '0B8KB9DRosYGKMXNoeWxqa3JYclE',
'ext': 'mp4',
'title': 'Jimmy Fallon Sings Since You\'ve Been Gone.wmv',
}
}
@staticmethod
def _extract_url(webpage):
mobj = re.search(
2015-07-17 13:17:19 +00:00
r'<iframe src="https?://(?:video\.google\.com/get_player\?.*?docid=|(?:docs|drive)\.google\.com/file/d/)(?P<id>[a-zA-Z0-9_-]{28})',
2015-06-29 06:53:21 +00:00
webpage)
if mobj:
return 'https://drive.google.com/file/d/%s' % mobj.group('id')
def _real_extract(self, url):
video_id = self._match_id(url)
return {
'_type': 'url',
'ie-key': 'GoogleDrive',
'url': 'https://drive.google.com/file/d/%s' % video_id
}
2015-06-24 00:13:23 +00:00
class GoogleDriveIE(InfoExtractor):
2015-07-17 13:17:19 +00:00
_VALID_URL = r'https?://(?:docs|drive)\.google\.com/(?:uc\?.*?id=|file/d/)(?P<id>[a-zA-Z0-9_-]{28})'
2015-06-24 00:13:23 +00:00
_TEST = {
2015-06-24 13:56:19 +00:00
'url': 'https://drive.google.com/file/d/0ByeS4oOUV-49Zzh4R1J6R09zazQ/edit?pli=1',
2015-06-24 00:13:23 +00:00
'info_dict': {
2015-06-24 13:56:19 +00:00
'id': '0ByeS4oOUV-49Zzh4R1J6R09zazQ',
2015-06-24 00:13:23 +00:00
'ext': 'mp4',
2015-06-24 13:56:19 +00:00
'title': 'Big Buck Bunny.mp4',
2015-06-24 00:13:23 +00:00
}
}
_formats = {
'5': {'ext': 'flv'},
'6': {'ext': 'flv'},
'13': {'ext': '3gp'},
'17': {'ext': '3gp'},
'18': {'ext': 'mp4'},
'22': {'ext': 'mp4'},
'34': {'ext': 'flv'},
'35': {'ext': 'flv'},
'36': {'ext': '3gp'},
'37': {'ext': 'mp4'},
'38': {'ext': 'mp4'},
'43': {'ext': 'webm'},
'44': {'ext': 'webm'},
'45': {'ext': 'webm'},
'46': {'ext': 'webm'},
'59': {'ext': 'mp4'}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(
2015-07-17 13:37:21 +00:00
'http://docs.google.com/file/d/' + video_id, video_id, encoding='unicode_escape'
2015-06-24 00:13:23 +00:00
)
try:
title = self._html_search_regex(
2015-07-17 13:37:21 +00:00
r'"title"\s+,\s+"[^"]+',
2015-06-24 00:13:23 +00:00
webpage,
2015-07-17 13:37:21 +00:00
'title'
2015-06-24 00:13:23 +00:00
)
fmt_stream_map = self._html_search_regex(
2015-07-17 13:37:21 +00:00
r'"fmt_stream_map"\s+,\s+"[^"]+',
2015-06-24 00:13:23 +00:00
webpage,
2015-07-17 13:37:21 +00:00
'fmt_stream_map'
2015-06-24 00:13:23 +00:00
)
fmt_list = self._html_search_regex(
2015-07-17 13:37:21 +00:00
r'"fmt_list"\s+,\s+"[^"]+',
2015-06-24 00:13:23 +00:00
webpage,
2015-07-17 13:37:21 +00:00
'fmt_list'
2015-06-24 00:13:23 +00:00
)
# timestamp = self._html_search_regex(
2015-07-17 13:37:21 +00:00
# r'"timestamp"\s+,\s+"[^"]+',
2015-06-24 00:13:23 +00:00
# webpage,
2015-07-17 13:37:21 +00:00
# 'timestamp'
2015-06-24 00:13:23 +00:00
# )
length_seconds = self._html_search_regex(
2015-07-17 13:37:21 +00:00
r'"length_seconds"\s+,\s+"[^"]+',
2015-06-24 00:13:23 +00:00
webpage,
2015-07-17 13:37:21 +00:00
'length_seconds'
2015-06-24 00:13:23 +00:00
)
except RegexNotFoundError:
try:
reason = self._html_search_regex(
2015-07-17 13:37:21 +00:00
r'"reason","[^"]+',
2015-06-24 00:13:23 +00:00
webpage,
2015-07-17 13:37:21 +00:00
'reason'
2015-06-24 00:13:23 +00:00
)
self.report_warning(reason)
return
except RegexNotFoundError:
self.report_warning('not a video')
return
fmt_stream_map = fmt_stream_map.split(',')
fmt_list = fmt_list.split(',')
formats = []
for i in range(len(fmt_stream_map)):
fmt_id, fmt_url = fmt_stream_map[i].split('|')
resolution = fmt_list[i].split('/')[1]
width, height = resolution.split('x')
formats.append({
'url': fmt_url,
'format_id': fmt_id,
'resolution': resolution,
'width': int(width),
'height': int(height),
'ext': self._formats[fmt_id]['ext']
})
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
# 'timestamp': int(timestamp),
'duration': int(length_seconds),
'formats': formats
}