R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

[generic] Look at all LD-JSON blobs, not just the first one

Browse Source
This commit is contained in:
jesus 2019-03-14 16:13:37 +01:00
parent 6db03a29d1
commit d04d262af8
1 changed files with 27 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
youtube_dl/extractor/common.py
View File

@ -965,17 +965,26 @@ class InfoExtractor(object):
video_info['description'] = playlist_description video_info['description'] = playlist_description
return video_info return video_info
def _search_regex(self, pattern, string, name, default=NO_DEFAULT, fatal=True, flags=0, group=None): def _search_regex(self, pattern, string, name, default=NO_DEFAULT, fatal=True, flags=0, group=None, return_all=False):
""" """
Perform a regex search on the given string, using a single or a list of Perform a regex search on the given string, using a single or a list of
patterns returning the first matching group. patterns returning the first matching group.
In case of failure return a default value or raise a WARNING or a In case of failure return a default value or raise a WARNING or a
RegexNotFoundError, depending on fatal, specifying the field name. RegexNotFoundError, depending on fatal, specifying the field name.
""" """
matches = []
if isinstance(pattern, (str, compat_str, compiled_regex_type)): if isinstance(pattern, (str, compat_str, compiled_regex_type)):
if return_all:
matches = list(re.finditer(pattern, string, flags))
else:
mobj = re.search(pattern, string, flags) mobj = re.search(pattern, string, flags)
else: else:
for p in pattern: for p in pattern:
if return_all:
new_matches = list(re.finditer(p, string, flags))
matches.extend(new_matches)
else:
mobj = re.search(p, string, flags) mobj = re.search(p, string, flags)
if mobj: if mobj:
break break
@ -985,7 +994,12 @@ class InfoExtractor(object):
else: else:
_name = name _name = name
if mobj: if return_all and len(matches) > 0:
if group is None:
return list(map(lambda m: next(g for g in m.groups() if g is not None), matches))
else:
return list(map(lambda m: m.group(group), matches))
elif mobj:
if group is None: if group is None:
# return the first matching group # return the first matching group
return next(g for g in mobj.groups() if g is not None) return next(g for g in mobj.groups() if g is not None)
@ -1174,16 +1188,19 @@ class InfoExtractor(object):
'twitter card player') 'twitter card player')
def _search_json_ld(self, html, video_id, expected_type=None, **kwargs): def _search_json_ld(self, html, video_id, expected_type=None, **kwargs):
json_ld = self._search_regex( json_lds = self._search_regex(
JSON_LD_RE, html, 'JSON-LD', group='json_ld', **kwargs) JSON_LD_RE, html, 'JSON-LD', group='json_ld', return_all=True, **kwargs)
default = kwargs.get('default', NO_DEFAULT) default = kwargs.get('default', NO_DEFAULT)
if not json_ld: if not json_lds or len(json_lds) == 0:
return default if default is not NO_DEFAULT else {} return default if default is not NO_DEFAULT else {}
# JSON-LD may be malformed and thus `fatal` should be respected. # JSON-LD may be malformed and thus `fatal` should be respected.
# At the same time `default` may be passed that assumes `fatal=False` # At the same time `default` may be passed that assumes `fatal=False`
# for _search_regex. Let's simulate the same behavior here as well. # for _search_regex. Let's simulate the same behavior here as well.
fatal = kwargs.get('fatal', True) if default == NO_DEFAULT else False fatal = kwargs.get('fatal', True) if default == NO_DEFAULT else False
return self._json_ld(json_ld, video_id, fatal=fatal, expected_type=expected_type) for json_ld in json_lds:
found = self._json_ld(json_ld, video_id, fatal=fatal, expected_type=expected_type)
if found:
return found
def _json_ld(self, json_ld, video_id, fatal=True, expected_type=None): def _json_ld(self, json_ld, video_id, fatal=True, expected_type=None):
if isinstance(json_ld, compat_str): if isinstance(json_ld, compat_str):