ofscraper-community 3.16.2__py3-none-any.whl

ofscraper/__main__.py

@@ -0,0 +1,9 @@
+import ofscraper.main.open.load as load
+
+
+def main():
+    load.main()
+
+
+if __name__ == "__main__":
+    main()

ofscraper/__version__.py

@@ -0,0 +1,13 @@
+from __future__ import annotations
+import importlib.metadata
+
+# The version is now read from the installed package's metadata
+try:
+    # The distribution is published as 'ofscraper-community'; the import
+    # package and the command are still 'ofscraper'. Keep the name a literal:
+    # PyInstaller looks for it to bundle the metadata into the binaries.
+    __version__ = importlib.metadata.version("ofscraper-community")
+except importlib.metadata.PackageNotFoundError:
+    # This is a fallback for cases where the package is not installed at all,
+    # or you are in a situation where metadata is not available.
+    __version__ = "0.0.0" # A sensible fallback

ofscraper/classes/labels.py

@@ -0,0 +1,40 @@
+import ofscraper.classes.of.posts as posts_
+
+
+class Label:
+    def __init__(self, label, model_id, username):
+        self._label_id = label.get("id")
+        self._name = label.get("name")
+        self._type = label.get("type")
+        self._posts = list(
+            map(
+                lambda x: posts_.Post(x, model_id, username, label=self._name),
+                label.get("posts"),
+            )
+        )
+        self._model_id = int(model_id)
+        self._username = username
+
+    @property
+    def model_id(self):
+        return self._model_id
+
+    @property
+    def username(self):
+        return self._username
+
+    @property
+    def label_id(self):
+        return self._label_id
+
+    @property
+    def name(self):
+        return self._name
+
+    @property
+    def type(self):
+        return self._type
+
+    @property
+    def posts(self):
+        return self._posts

ofscraper/classes/of/base.py

@@ -0,0 +1,54 @@
+import importlib
+import re
+
+from bs4 import BeautifulSoup
+
+import ofscraper.utils.settings as settings
+
+html_parser = "lxml" if importlib.util.find_spec("lxml") else "html.parser"
+
+
+class base:
+    def __init__(self):
+        None
+
+    def text_trunicate(self, text):
+        text = str(text)
+        if text is None:
+            return "None"
+        if len(text) == 0:
+            return text
+        length = int(settings.get_settings().text_length)
+        if length == 0:
+            return text
+        elif settings.get_settings().text_type == "letter":
+            return f"{''.join(list(text)[:length])}"
+        else:
+            # text has usually been through file_cleanup already, which swaps
+            # spaces for space_replacer, so words are split on that. If the
+            # original text already contained that character (e.g. "_" in a
+            # caption with "_" as the replacer), it also counts as a word
+            # break; the original spaces can't be told apart at this point.
+            sep = settings.get_settings().space_replacer or " "
+            if sep not in text:
+                sep = " "
+            words = [x for x in text.split(sep) if x]
+            text = sep.join(words[:length])
+        text = re.sub(" +$", "", text)
+        return text
+
+    def file_cleanup(self, text):
+        text = str(text)
+        text = re.sub("<[^>]*>", "", text)
+        text = re.sub(r'[\n<>:"/\|?*:;]+', "", text)
+        text = re.sub("-+", "_", text)
+        text = re.sub(" +", " ", text)
+        text = re.sub(" ", settings.get_settings().space_replacer, text)
+        return text
+
+    def db_cleanup(self, string):
+        string = string or ""
+        string = re.sub("<[^>]*>", "", string)
+        string = " ".join(string.split())
+        string = BeautifulSoup(string, html_parser).get_text()
+        return string