diff options
author | Sergey M․ <[email protected]> | 2018-06-02 01:32:18 +0700 |
---|---|---|
committer | Sergey M․ <[email protected]> | 2018-06-02 01:42:05 +0700 |
commit | 9b89daefa6fc3dbfce0d725283ecef753a8603ba (patch) | |
tree | 27d3fe5e83f5f366d5e62bac0f559c3adfc7b19b | |
parent | 9d082e7cb81c63dc5c2e616cd7ca7237a5e0d642 (diff) | |
download | youtube-dl-9b89daefa6fc3dbfce0d725283ecef753a8603ba.tar.gz youtube-dl-9b89daefa6fc3dbfce0d725283ecef753a8603ba.zip |
[facebook] Improve extraction (closes #16554)
-rw-r--r-- | youtube_dl/extractor/facebook.py | 62 |
1 files changed, 35 insertions, 27 deletions
diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py index 8bbca4f56..8a9ed96c2 100644 --- a/youtube_dl/extractor/facebook.py +++ b/youtube_dl/extractor/facebook.py @@ -324,47 +324,56 @@ class FacebookIE(InfoExtractor): if server_js_data: video_data = extract_video_data(server_js_data.get('instances', [])) + def extract_from_jsmods_instances(js_data): + if js_data: + return extract_video_data(try_get( + js_data, lambda x: x['jsmods']['instances'], list) or []) + if not video_data: server_js_data = self._parse_json( self._search_regex( r'bigPipe\.onPageletArrive\(({.+?})\)\s*;\s*}\s*\)\s*,\s*["\']onPageletArrive\s+(?:stream_pagelet|pagelet_group_mall|permalink_video_pagelet)', webpage, 'js data', default='{}'), video_id, transform_source=js_to_json, fatal=False) - if server_js_data: - video_data = extract_video_data(try_get( - server_js_data, lambda x: x['jsmods']['instances'], - list) or []) + video_data = extract_from_jsmods_instances(server_js_data) if not video_data: - # video info not in first request, do a secondary request using tahoe player specific url + if not fatal_if_no_video: + return webpage, False + m_msg = re.search(r'class="[^"]*uiInterstitialContent[^"]*"><div>(.*?)</div>', webpage) + if m_msg is not None: + raise ExtractorError( + 'The video is not available, Facebook said: "%s"' % m_msg.group(1), + expected=True) + elif '>You must log in to continue' in webpage: + self.raise_login_required() + + # Video info not in first request, do a secondary request using + # tahoe player specific URL tahoe_data = self._download_webpage( self._VIDEO_PAGE_TAHOE_TEMPLATE % video_id, video_id, data=urlencode_postdata({ '__user': 0, '__a': 1, - '__pc': self._search_regex(r'"pkg_cohort":"(.*?)"', webpage, 'pkg cohort', default='PHASED:DEFAULT'), - '__rev': self._search_regex(r'"client_revision":(\d+),', webpage, 'client revision', default=3944515), + '__pc': self._search_regex( + r'pkg_cohort["\']\s*:\s*["\'](.+?)["\']', webpage, + 'pkg cohort', default='PHASED:DEFAULT'), + '__rev': self._search_regex( + r'client_revision["\']\s*:\s*(\d+),', webpage, + 'client revision', default='3944515'), }), headers={ 'Content-Type': 'application/x-www-form-urlencoded', }) - tahoe_js_data = self._parse_json(self._search_regex( - r'for \(;;\);(.+)', tahoe_data, - 'tahoe js data', default='{}'), video_id, fatal=False) - video_data = extract_video_data(tahoe_js_data.get('jsmods', {}).get('instances', [])) + tahoe_js_data = self._parse_json( + self._search_regex( + r'for\s+\(\s*;\s*;\s*\)\s*;(.+)', tahoe_data, + 'tahoe js data', default='{}'), + video_id, fatal=False) + video_data = extract_from_jsmods_instances(tahoe_js_data) if not video_data: - if not fatal_if_no_video: - return webpage, False - m_msg = re.search(r'class="[^"]*uiInterstitialContent[^"]*"><div>(.*?)</div>', webpage) - if m_msg is not None: - raise ExtractorError( - 'The video is not available, Facebook said: "%s"' % m_msg.group(1), - expected=True) - elif '>You must log in to continue' in webpage: - self.raise_login_required() - else: - raise ExtractorError('Cannot parse data') + raise ExtractorError('Cannot parse data') formats = [] for f in video_data: @@ -408,11 +417,10 @@ class FacebookIE(InfoExtractor): video_title = limit_length(video_title, 80) else: video_title = 'Facebook video #%s' % video_id - uploader = clean_html(get_element_by_id('fbPhotoPageAuthorName', webpage)) - if not uploader: - uploader = self._search_regex( - [r'ownerName\s*:\s*"([^"]+)"', r'property="og:title"\s*content="(.*?)"'], - webpage, 'uploader', fatal=False) + uploader = clean_html(get_element_by_id( + 'fbPhotoPageAuthorName', webpage)) or self._search_regex( + r'ownerName\s*:\s*"([^"]+)"', webpage, 'uploader', + fatal=False) or self._og_search_title(webpage, fatal=False) timestamp = int_or_none(self._search_regex( r'<abbr[^>]+data-utime=["\'](\d+)', webpage, 'timestamp', default=None)) |