yt-dlc/youtube_dl/extractor/googledrive.py
Yen Chi Hsuan e4e50f60b1
[googledrive] Fix extraction on Python 3.6
Since Python 3.6, invalid escape sequences are deprecated. It's likely
that there are invalid escape sequences somewhere on the webpage, so
instead of unescaping the whole webpage, just unescape the URL.

See https://bugs.python.org/issue27364. That change was designed for
string literals, while it affects the 'unicode_escape' encoding as well.
The code path is:

str.decode('unicode_escape')
    codecs.unicode_escape_decode()
        PyUnicode_DecodeUnicodeEscape()
2017-02-05 21:41:08 +08:00

94 lines
3.1 KiB
Python

from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
int_or_none,
lowercase_escape,
)
class GoogleDriveIE(InfoExtractor):
_VALID_URL = r'https?://(?:(?:docs|drive)\.google\.com/(?:uc\?.*?id=|file/d/)|video\.google\.com/get_player\?.*?docid=)(?P<id>[a-zA-Z0-9_-]{28,})'
_TESTS = [{
'url': 'https://drive.google.com/file/d/0ByeS4oOUV-49Zzh4R1J6R09zazQ/edit?pli=1',
'md5': 'd109872761f7e7ecf353fa108c0dbe1e',
'info_dict': {
'id': '0ByeS4oOUV-49Zzh4R1J6R09zazQ',
'ext': 'mp4',
'title': 'Big Buck Bunny.mp4',
'duration': 45,
}
}, {
# video id is longer than 28 characters
'url': 'https://drive.google.com/file/d/1ENcQ_jeCuj7y19s66_Ou9dRP4GKGsodiDQ/edit',
'only_matching': True,
}]
_FORMATS_EXT = {
'5': 'flv',
'6': 'flv',
'13': '3gp',
'17': '3gp',
'18': 'mp4',
'22': 'mp4',
'34': 'flv',
'35': 'flv',
'36': '3gp',
'37': 'mp4',
'38': 'mp4',
'43': 'webm',
'44': 'webm',
'45': 'webm',
'46': 'webm',
'59': 'mp4',
}
@staticmethod
def _extract_url(webpage):
mobj = re.search(
r'<iframe[^>]+src="https?://(?:video\.google\.com/get_player\?.*?docid=|(?:docs|drive)\.google\.com/file/d/)(?P<id>[a-zA-Z0-9_-]{28,})',
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)
webpage = self._download_webpage(
'http://docs.google.com/file/d/%s' % video_id, video_id)
reason = self._search_regex(r'"reason"\s*,\s*"([^"]+)', webpage, 'reason', default=None)
if reason:
raise ExtractorError(reason)
title = self._search_regex(r'"title"\s*,\s*"([^"]+)', webpage, 'title')
duration = int_or_none(self._search_regex(
r'"length_seconds"\s*,\s*"([^"]+)', webpage, 'length seconds', default=None))
fmt_stream_map = self._search_regex(
r'"fmt_stream_map"\s*,\s*"([^"]+)', webpage, 'fmt stream map').split(',')
fmt_list = self._search_regex(r'"fmt_list"\s*,\s*"([^"]+)', webpage, 'fmt_list').split(',')
formats = []
for fmt, fmt_stream in zip(fmt_list, fmt_stream_map):
fmt_id, fmt_url = fmt_stream.split('|')
resolution = fmt.split('/')[1]
width, height = resolution.split('x')
formats.append({
'url': lowercase_escape(fmt_url),
'format_id': fmt_id,
'resolution': resolution,
'width': int_or_none(width),
'height': int_or_none(height),
'ext': self._FORMATS_EXT[fmt_id],
})
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'thumbnail': self._og_search_thumbnail(webpage, default=None),
'duration': duration,
'formats': formats,
}