erjemin/instaloader
erjemin/instaloader
1
0
Fork 0
Code Issues Wiki Activity

Fix and globalize regex

Browse Source
This commit is contained in:
MiguelX413 2022-07-15 12:14:16 -07:00 committed by Alexander Graf
parent 0c21da8c18
commit 8784ac7d9b
1 changed files with 20 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
instaloader/structures.py
View File

@ -73,6 +73,22 @@ PostLocation.has_public_page.__doc__ = "Whether location has a public page."
PostLocation.lat.__doc__ = "Latitude (:class:`float` or None)." PostLocation.lat.__doc__ = "Latitude (:class:`float` or None)."
PostLocation.lng.__doc__ = "Longitude (:class:`float` or None)." PostLocation.lng.__doc__ = "Longitude (:class:`float` or None)."
# This regular expression is by MiguelX413
_hashtag_regex = re.compile(r"(?:#)((?:\w){1,150})")
# This regular expression is modified from jStassen, adjusted to use Python's \w to
# support Unicode and a word/beginning of string delimiter at the beginning to ensure
# that no email addresses join the list of mentions.
# http://blog.jstassen.com/2016/03/code-regex-for-instagram-username-and-hashtags/
_mention_regex = re.compile(r"(?:^|[^\w\n]|_)(?:@)(\w(?:(?:\w|(?:\.(?!\.))){0,28}(?:\w))?)", re.ASCII)
def _optional_normalize(string: Optional[str]) -> Optional[str]:
if string is not None:
return normalize("NFC", string)
else:
return None
class Post: class Post:
""" """
@ -396,16 +412,10 @@ class Post:
@property @property
def caption(self) -> Optional[str]: def caption(self) -> Optional[str]:
"""Caption.""" """Caption."""
def _normalize(string: Optional[str]) -> Optional[str]:
if string is not None:
return normalize("NFC", string)
else:
return None
if "edge_media_to_caption" in self._node and self._node["edge_media_to_caption"]["edges"]: if "edge_media_to_caption" in self._node and self._node["edge_media_to_caption"]["edges"]:
return _normalize(self._node["edge_media_to_caption"]["edges"][0]["node"]["text"]) return _optional_normalize(self._node["edge_media_to_caption"]["edges"][0]["node"]["text"])
elif "caption" in self._node: elif "caption" in self._node:
return _normalize(self._node["caption"]) return _optional_normalize(self._node["caption"])
return None return None
@property @property
@ -413,22 +423,14 @@ class Post:
"""List of all lowercased hashtags (without preceeding #) that occur in the Post's caption.""" """List of all lowercased hashtags (without preceeding #) that occur in the Post's caption."""
if not self.caption: if not self.caption:
return [] return []
# This regular expression is from jStassen, adjusted to use Python's \w to support Unicode return _hashtag_regex.findall(self.caption.lower())
# http://blog.jstassen.com/2016/03/code-regex-for-instagram-username-and-hashtags/
hashtag_regex = re.compile(r"(?:#)(\w(?:(?:\w|(?:\.(?!\.))){0,28}(?:\w))?)")
return re.findall(hashtag_regex, self.caption.lower())
@property @property
def caption_mentions(self) -> List[str]: def caption_mentions(self) -> List[str]:
"""List of all lowercased profiles that are mentioned in the Post's caption, without preceeding @.""" """List of all lowercased profiles that are mentioned in the Post's caption, without preceeding @."""
if not self.caption: if not self.caption:
return [] return []
# This regular expression is modified from jStassen, adjusted to use Python's \w to return _mention_regex.findall(self.caption.lower())
# support Unicode and a word/beginning of string delimiter at the beginning to ensure
# that no email addresses join the list of mentions.
# http://blog.jstassen.com/2016/03/code-regex-for-instagram-username-and-hashtags/
mention_regex = re.compile(r"(?:^|\W|_)(?:@)(\w(?:(?:\w|(?:\.(?!\.))){0,28}(?:\w))?)", re.ASCII)
return re.findall(mention_regex, self.caption.lower())
@property @property
def pcaption(self) -> str: def pcaption(self) -> str: