Implemented search functionality

src/dvd-compare-python/dvd_compare.py

@@ -13,8 +13,10 @@ class DcSearchResult:
         """Year of media parsed from label. Parsing has not been tested on all cases."""
         self.title: str
         """Title of media parsed from label. Parsing has not been tested on all cases."""
+        self.tagline: str
+        """Unprocessed tagline returned by search."""
         self.format: str
-        """Format (DVD, Blu-Ray, etc.) parsed from label. Parsing has not been tested on all cases."""
+        """Format (DVD, Blu-Ray, etc.) parsed from label. Defaults to DVD if no explicit format is given. Parsing has not been tested on all cases."""
         self.fid: int
         """FID, used to identify media by dvdcompare.net, parsed from URL. Can be used to retrive further details."""
         self.url: str
@@ -23,7 +25,7 @@ class DcSearchResult:
         """Description, listing available publications to label, as returned by search."""
 
     def __repr__(self):
-        return f"{self.label}\n{self.description}\n"
+        return f"{self.label}\n{self.title} | {self.format} | {self.year}\n{self.tagline}\n[{self.fid} | {self.url}]\n{self.description}\n"
 
 
 class DvdCompare:
@@ -33,10 +35,35 @@ class DvdCompare:
     """ Can be adjusted, if the domain should ever be changed."""
 
     def _reduce_spaces(text: str) -> str:
-        return re.sub(r"\s+", " ", text)
-    
-    def _get_title(label: str) -> str:
-        
+        return re.sub(r"\s+", " ", text).strip()
+
+    def _parse_result(item) -> DcSearchResult:
+        result = DcSearchResult()
+
+        # Get direct values
+        result.label = DvdCompare._reduce_spaces(item.strong.a.text)
+        result.description = DvdCompare._reduce_spaces(
+            f"{item.find('i').text}{list(item.children)[4]}"
+        )
+        result.url = f"{DvdCompare.BASE_URL}/comparisons/{item.strong.a.get('href')}"
+        result.tagline = item.strong.a.get("title")
+
+        # Parse QoL values
+        label_matches = re.match(
+            r"^(?P<title>[^()]+)\s(?P<the>\(The\))?\s?(?:\((?P<format>[^()]+)\))?\s?\((?P<year>[0-9]{4})\)$",
+            result.label,
+            re.IGNORECASE,
+        )
+
+        result.format = label_matches["format"] if label_matches["format"] else "DVD"
+        result.year = int(label_matches["year"])
+        result.title = label_matches["title"]
+        if label_matches["the"]:
+            result.title = f"The {result.title}"
+
+        result.fid = int(result.url.split("?fid=")[1])
+
+        return result
 
     async def search_async(
         title: str | None,
@@ -93,15 +120,7 @@ class DvdCompare:
         if result_parent is None:
             return []  # Nothing found
 
-        all_results = []
-        for child in result_parent.find_all("li"):
-            next_result = DcSearchResult()
-            next_result.label = DvdCompare._reduce_spaces(child.strong.a.text)
-            next_result.description = DvdCompare._reduce_spaces(f"{child.find('i').text}{list(child.children)[4]}")
-
-            all_results.append(next_result)
-
-        return all_results
+        return [DvdCompare._parse_result(i) for i in result_parent.find_all("li")]
 
 
 if __name__ == "__main__":