Merge pull request #1037 from fa0311/fix/script-loading

fix: escape regex in twitter.py, md_generator.py, legacy.py, js_parse…

Author: fa0311

lib/graphql.py

@@ -8,14 +8,14 @@
 
 
 def get_graphql(parsed_list: JsData) -> list:
-    reg_graphql = "e\.graphQL\({func}\(\),$".format(func="([a-zA-Z_\$]{1,2})")
+    reg_graphql = r"e\.graphQL\({func}\(\),$".format(func=r"([a-zA-Z_$]{1,2})")
     graphql_list = search_js_reg(parsed_list, reg_graphql)
     graphql_output = []
 
     for graphql in tqdm(graphql_list):
-        reg_func = "{func}=t.n\({arg}\)".format(
+        reg_func = r"{func}=t.n\({arg}\)".format(
             func=re.escape(graphql.data[0]),
-            arg="([a-zA-Z_\$]{1,2})",
+            arg=r"([a-zA-Z_$]{1,2})",
         )
 
         graphql_parent = graphql.parent
@@ -28,9 +28,9 @@ def get_graphql(parsed_list: JsData) -> list:
 
         if match_func == []:
             continue
-        reg_func_init = "{func}=t\({arg}\)".format(
+        reg_func_init = r"{func}=t\({arg}\)".format(
             func=re.escape(match_func[0].data[0]),
-            arg="([0-9]{1,5})",
+            arg=r"([0-9]{1,5})",
         )
         match_func_init = search_js_reg(graphql_parent, reg_func_init)
         if match_func_init == []:
@@ -58,7 +58,7 @@ def marge_exports(parsed_list: list, graphql_output: list) -> list:
     reg_exports = "{comma}{int}:{var}=>".format(
         comma=",?",
         int="([0-9]{1,5})",
-        var="(e|\([a-z,]*?\))",
+        var=r"(e|\([a-z,]*?\))",
     )
     for export in exports:
         n = re.findall(reg_exports, export.parent.before)[0][0]
@@ -142,7 +142,7 @@ def marge_metadata(graphql_output: list, feature_switch: dict) -> list:
 
 
 def get_freeze_object(parsed_list: list, disable_tqdm=True) -> list:
-    reg_freeze_object = "Object\.freeze\($"
+    reg_freeze_object = r"Object\.freeze\($"
     freeze_object_list = search_js_reg(parsed_list, reg_freeze_object)
     freeze_object_output = []
 
@@ -158,7 +158,7 @@ def get_freeze_object(parsed_list: list, disable_tqdm=True) -> list:
 
 
 def get_feature_switches(parsed_list: list) -> list:
-    reg_exports = "e\.exports={var}$".format(var="([a-zA-Z]{1,2})")
+    reg_exports = r"e\.exports={var}$".format(var=r"([a-zA-Z]{1,2})")
     exports_list = search_js_reg(parsed_list, reg_exports)
     for exports in exports_list:
         feature_switches = get_freeze_object(exports.parent, disable_tqdm=True)

lib/js_parser/js_parser.py

@@ -119,7 +119,7 @@ def search_js_reg(text: JsData, search: str) -> list[JsSearchData]:
 
 def json_parser(text: JsData):
     output = ""
-    reg_other = "[0-9a-zA-Z\s" + re.escape("!?$_.{}&=") + "]"
+    reg_other = r"[0-9a-zA-Z\s" + re.escape("!?$_.{}&=") + "]"
     for data in text.children:
         if type(data) is JsData:
             json = json_parser(data)
@@ -133,14 +133,14 @@ def json_parser(text: JsData):
             placeholder = parentheses_placeholder(data)
             json_child = ""
             json = re.sub(
-                f"(,|^)(\.\.\.{reg_other}+)(,|$)",
+                rf"(,|^)(\.\.\.{reg_other}+)(,|$)",
                 r'\1"\2":"_"\3',
                 placeholder.text,
             )
             while json_child != json:
                 json_child = json
                 json = re.sub(
-                    f"(,|^)(\.\.\.{reg_other}+)(,|$)",
+                    rf"(,|^)(\.\.\.{reg_other}+)(,|$)",
                     r'\1"\2":"_"\3',
                     json_child,
                 )

lib/legacy.py

@@ -20,9 +20,9 @@ def get_dispatch_list():
 
 
 def get_dispatch(parsed_list: JsData) -> dict:
-    reg_graphql = 'e.{method}\("{queryId}",'.format(
+    reg_graphql = r'e.{method}\("{queryId}",'.format(
         method="({0})".format("|".join(get_dispatch_list().keys())),
-        queryId="([a-z_/]*?)",
+        queryId=r"([a-z_/]*?)",
     )
     dispatch_list = search_js_reg(parsed_list, reg_graphql)
     dispatch_list_unique: list[JsSearchData] = []

lib/md_generator/md_generator.py

@@ -35,7 +35,7 @@ def table(self, data: dict, end: str = "\n\n"):
 
     def table_escape(self, text: str):
         if type(text) is str:
-            return text.replace("|", "\|")
+            return text.replace("|", r"\|")
         else:
             return text
 

lib/twitter.py

@@ -81,19 +81,19 @@ def get_header(self):
         }
 
     def get_script_url(self) -> list[str]:
-        src = "(https://abs\.twimg\.com\/{0}\/client-web\/[a-zA-Z0-9\.]*?\.js)".format(
+        src = r"(https://abs\.twimg\.com\/{0}\/client-web\/[a-zA-Z0-9\.]*?\.js)".format(
             re.escape(self.CLIENT)
         )
         reg_script = '<script type="text/javascript" charset="utf-8" nonce="{nonce}" crossorigin="anonymous" src="{src}"></script>'.format(
-            nonce="([a-zA-Z0-9]{48})",
+            nonce=r"([a-zA-Z0-9]{48})",
             src=src,
         )
         return [url[1] for url in re.findall(reg_script, self.response.text)]
 
     def get_script(self, response: str) -> list[str]:
         reg_script = '<script type="text/javascript" charset="utf-8" nonce="{nonce}">{any}</script>'.format(
-            nonce="([a-zA-Z0-9]{48})",
-            any="([\s\S]*?)",
+            nonce=r"([a-zA-Z0-9]{48})",
+            any=r"([\s\S]*?)",
         )
         return [script[1] for script in re.findall(reg_script, response)]