Initial

python/web/mal_top_fetcher.py

@@ -0,0 +1,34 @@
+import requests, bs4, time
+
+def get_titles(filename, title_type, maxrank):
+    with open(filename, "w", encoding="UTF-8") as file:
+        limit = 0
+        written = 0
+
+        while True:
+            page = requests.get("https://myanimelist.net/topanime.php?type=" + title_type + "&limit=" + str(limit), headers = {'User-agent': 'stopblockingmyscriptlol'})
+            page.raise_for_status()
+
+            soup = bs4.BeautifulSoup(page.text, "html.parser")
+
+            titles = soup.select("a[rel]")
+
+            for title in titles:
+                if len(title.text) == 2 or title.text == "Login":
+                    continue
+
+                file.write(title.text.strip() + '\n')
+                written += 1
+
+                print(str(written), title.text.strip())
+
+                if written >= maxrank:
+                    break
+
+            if written >= maxrank:
+                break
+
+            limit += 50
+
+get_titles("rating.txt", "tv", 1750)
+get_titles("movies.txt", "movie", 300)