From 945803f65d79d0277c663a0e043228ed10996a92 Mon Sep 17 00:00:00 2001
From: Caeden Perelli-Harris <caedenperelliharris@gmail.com>
Date: Fri, 18 Aug 2023 13:19:25 +0100
Subject: [PATCH] Unmark fetch anime and play as BROKEN and fix type errors 
 (#8988)

* updating DIRECTORY.md

* type(fetch-anime-and-play): Fix type errors and re-enable

* updating DIRECTORY.md

---------

Co-authored-by: github-actions <${GITHUB_ACTOR}@users.noreply.github.com>
---
 DIRECTORY.md                                  |  1 +
 ...play.py.BROKEN => fetch_anime_and_play.py} | 71 ++++++++++---------
 2 files changed, 38 insertions(+), 34 deletions(-)
 rename web_programming/{fetch_anime_and_play.py.BROKEN => fetch_anime_and_play.py} (70%)

diff --git a/DIRECTORY.md b/DIRECTORY.md
index 1ff093d88..6af4ead56 100644
--- a/DIRECTORY.md
+++ b/DIRECTORY.md
@@ -1213,6 +1213,7 @@
   * [Daily Horoscope](web_programming/daily_horoscope.py)
   * [Download Images From Google Query](web_programming/download_images_from_google_query.py)
   * [Emails From Url](web_programming/emails_from_url.py)
+  * [Fetch Anime And Play](web_programming/fetch_anime_and_play.py)
   * [Fetch Bbc News](web_programming/fetch_bbc_news.py)
   * [Fetch Github Info](web_programming/fetch_github_info.py)
   * [Fetch Jobs](web_programming/fetch_jobs.py)
diff --git a/web_programming/fetch_anime_and_play.py.BROKEN b/web_programming/fetch_anime_and_play.py
similarity index 70%
rename from web_programming/fetch_anime_and_play.py.BROKEN
rename to web_programming/fetch_anime_and_play.py
index 3bd4f704d..366807785 100644
--- a/web_programming/fetch_anime_and_play.py.BROKEN
+++ b/web_programming/fetch_anime_and_play.py
@@ -1,7 +1,5 @@
-from xml.dom import NotFoundErr
-
 import requests
-from bs4 import BeautifulSoup, NavigableString
+from bs4 import BeautifulSoup, NavigableString, Tag
 from fake_useragent import UserAgent
 
 BASE_URL = "https://ww1.gogoanime2.org"
@@ -41,25 +39,23 @@ def search_scraper(anime_name: str) -> list:
 
     # get list of anime
     anime_ul = soup.find("ul", {"class": "items"})
+    if anime_ul is None or isinstance(anime_ul, NavigableString):
+        msg = f"Could not find and anime with name {anime_name}"
+        raise ValueError(msg)
     anime_li = anime_ul.children
 
     # for each anime, insert to list. the name and url.
     anime_list = []
     for anime in anime_li:
-        if not isinstance(anime, NavigableString):
-            try:
-                anime_url, anime_title = (
-                    anime.find("a")["href"],
-                    anime.find("a")["title"],
-                )
-                anime_list.append(
-                    {
-                        "title": anime_title,
-                        "url": anime_url,
-                    }
-                )
-            except (NotFoundErr, KeyError):
-                pass
+        if isinstance(anime, Tag):
+            anime_url = anime.find("a")
+            if anime_url is None or isinstance(anime_url, NavigableString):
+                continue
+            anime_title = anime.find("a")
+            if anime_title is None or isinstance(anime_title, NavigableString):
+                continue
+
+            anime_list.append({"title": anime_title["title"], "url": anime_url["href"]})
 
     return anime_list
 
@@ -93,22 +89,24 @@ def search_anime_episode_list(episode_endpoint: str) -> list:
 
     # With this id. get the episode list.
     episode_page_ul = soup.find("ul", {"id": "episode_related"})
+    if episode_page_ul is None or isinstance(episode_page_ul, NavigableString):
+        msg = f"Could not find any anime eposiodes with name {anime_name}"
+        raise ValueError(msg)
     episode_page_li = episode_page_ul.children
 
     episode_list = []
     for episode in episode_page_li:
-        try:
-            if not isinstance(episode, NavigableString):
-                episode_list.append(
-                    {
-                        "title": episode.find("div", {"class": "name"}).text.replace(
-                            " ", ""
-                        ),
-                        "url": episode.find("a")["href"],
-                    }
-                )
-        except (KeyError, NotFoundErr):
-            pass
+        if isinstance(episode, Tag):
+            url = episode.find("a")
+            if url is None or isinstance(url, NavigableString):
+                continue
+            title = episode.find("div", {"class": "name"})
+            if title is None or isinstance(title, NavigableString):
+                continue
+
+            episode_list.append(
+                {"title": title.text.replace(" ", ""), "url": url["href"]}
+            )
 
     return episode_list
 
@@ -140,11 +138,16 @@ def get_anime_episode(episode_endpoint: str) -> list:
 
     soup = BeautifulSoup(response.text, "html.parser")
 
-    try:
-        episode_url = soup.find("iframe", {"id": "playerframe"})["src"]
-        download_url = episode_url.replace("/embed/", "/playlist/") + ".m3u8"
-    except (KeyError, NotFoundErr) as e:
-        raise e
+    url = soup.find("iframe", {"id": "playerframe"})
+    if url is None or isinstance(url, NavigableString):
+        msg = f"Could not find url and download url from {episode_endpoint}"
+        raise RuntimeError(msg)
+
+    episode_url = url["src"]
+    if not isinstance(episode_url, str):
+        msg = f"Could not find url and download url from {episode_endpoint}"
+        raise RuntimeError(msg)
+    download_url = episode_url.replace("/embed/", "/playlist/") + ".m3u8"
 
     return [f"{BASE_URL}{episode_url}", f"{BASE_URL}{download_url}"]