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>
This commit is contained in:
Caeden Perelli-Harris 2023-08-18 13:19:25 +01:00 committed by GitHub
parent 5f7819e1cd
commit 945803f65d
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 38 additions and 34 deletions

View File

@ -1213,6 +1213,7 @@
* [Daily Horoscope](web_programming/daily_horoscope.py) * [Daily Horoscope](web_programming/daily_horoscope.py)
* [Download Images From Google Query](web_programming/download_images_from_google_query.py) * [Download Images From Google Query](web_programming/download_images_from_google_query.py)
* [Emails From Url](web_programming/emails_from_url.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 Bbc News](web_programming/fetch_bbc_news.py)
* [Fetch Github Info](web_programming/fetch_github_info.py) * [Fetch Github Info](web_programming/fetch_github_info.py)
* [Fetch Jobs](web_programming/fetch_jobs.py) * [Fetch Jobs](web_programming/fetch_jobs.py)

View File

@ -1,7 +1,5 @@
from xml.dom import NotFoundErr
import requests import requests
from bs4 import BeautifulSoup, NavigableString from bs4 import BeautifulSoup, NavigableString, Tag
from fake_useragent import UserAgent from fake_useragent import UserAgent
BASE_URL = "https://ww1.gogoanime2.org" BASE_URL = "https://ww1.gogoanime2.org"
@ -41,25 +39,23 @@ def search_scraper(anime_name: str) -> list:
# get list of anime # get list of anime
anime_ul = soup.find("ul", {"class": "items"}) 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 anime_li = anime_ul.children
# for each anime, insert to list. the name and url. # for each anime, insert to list. the name and url.
anime_list = [] anime_list = []
for anime in anime_li: for anime in anime_li:
if not isinstance(anime, NavigableString): if isinstance(anime, Tag):
try: anime_url = anime.find("a")
anime_url, anime_title = ( if anime_url is None or isinstance(anime_url, NavigableString):
anime.find("a")["href"], continue
anime.find("a")["title"], anime_title = anime.find("a")
) if anime_title is None or isinstance(anime_title, NavigableString):
anime_list.append( continue
{
"title": anime_title, anime_list.append({"title": anime_title["title"], "url": anime_url["href"]})
"url": anime_url,
}
)
except (NotFoundErr, KeyError):
pass
return anime_list return anime_list
@ -93,22 +89,24 @@ def search_anime_episode_list(episode_endpoint: str) -> list:
# With this id. get the episode list. # With this id. get the episode list.
episode_page_ul = soup.find("ul", {"id": "episode_related"}) 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_page_li = episode_page_ul.children
episode_list = [] episode_list = []
for episode in episode_page_li: for episode in episode_page_li:
try: if isinstance(episode, Tag):
if not isinstance(episode, NavigableString): 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( episode_list.append(
{ {"title": title.text.replace(" ", ""), "url": url["href"]}
"title": episode.find("div", {"class": "name"}).text.replace(
" ", ""
),
"url": episode.find("a")["href"],
}
) )
except (KeyError, NotFoundErr):
pass
return episode_list return episode_list
@ -140,11 +138,16 @@ def get_anime_episode(episode_endpoint: str) -> list:
soup = BeautifulSoup(response.text, "html.parser") soup = BeautifulSoup(response.text, "html.parser")
try: url = soup.find("iframe", {"id": "playerframe"})
episode_url = soup.find("iframe", {"id": "playerframe"})["src"] 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" download_url = episode_url.replace("/embed/", "/playlist/") + ".m3u8"
except (KeyError, NotFoundErr) as e:
raise e
return [f"{BASE_URL}{episode_url}", f"{BASE_URL}{download_url}"] return [f"{BASE_URL}{episode_url}", f"{BASE_URL}{download_url}"]