Created
November 3, 2019 18:26
-
-
Save rohitkg98/ffde7b2dddba4e86ca5521f661c19c06 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import os | |
import requests | |
import argparse | |
from html.parser import HTMLParser | |
parser = argparse.ArgumentParser(description='Input Link required.') | |
parser.add_argument('root_url', help='Link to the download page of Anime.') | |
def get_api_url(root_url): | |
base_url = 'https://horriblesubs.info/api.php?method=getshows&type=show&showid=' | |
resp = requests.get(root_url) | |
# showid is of format 'var showid = ###;' | |
# first get find show id in the html and we remove the part after the ';' | |
# then we split at =, giving us ['showid' , '=', '###'], last element is the show id | |
showid = resp.text[resp.text.find('showid'):]\ | |
.split(';')[0]\ | |
.split('=')[-1]\ | |
.strip() | |
# add showid to base url and return it | |
return base_url + showid | |
def get_links_page(api_url): | |
full_text = '' | |
page_counter = 0 | |
extended_url = f"{api_url}&nextid={page_counter}" | |
resp = requests.get(extended_url) | |
while resp.text != 'DONE': | |
full_text += resp.text | |
page_counter += 1 | |
extended_url = f"{api_url}&nextid={page_counter}" | |
resp = requests.get(extended_url) | |
return full_text | |
def parse_and_save(parser, html_text, file_name): | |
rel_path = os.path.join(os.getcwd(), file_name) | |
os.mkdir(rel_path) | |
parser.feed(html_text) | |
for key, value in parser.data.items(): | |
os.mkdir(os.path.join(rel_path, key)) | |
for types, links in value.items(): | |
with open(os.path.join(rel_path, key, types), 'w') as file: | |
for link in links: | |
file.write(f'{link} \n') | |
# HTML Parser for Horrible Subs Download page | |
class HorribleSubsParser(HTMLParser): | |
tags = [] | |
current_category = '480p' | |
data = { | |
'480p': {}, | |
'720p': {}, | |
'1080p': {} | |
} | |
def handle_starttag(self, tag, attrs): | |
if len(attrs) > 1 and tag == 'a': | |
if attrs[0][1] in self.data[self.current_category].keys(): | |
self.data[self.current_category][attrs[0][1]].append(attrs[1][1]) | |
else: | |
self.data[self.current_category][attrs[0][1]] = [attrs[1][1]] | |
def handle_data(self, data): | |
if self.current_category not in data: | |
if '480p' in data: | |
self.current_category = '480p' | |
if '720p' in data: | |
self.current_category = '720p' | |
if '1080p' in data: | |
self.current_category = '1080p' | |
if __name__ == "__main__": | |
args = parser.parse_args() | |
# get api url | |
api_url = get_api_url(args.root_url) | |
# get the html page in string form | |
full_html = get_links_page(api_url) | |
# create parser object and parse the html | |
html_parser = HorribleSubsParser() | |
show_name = args.root_url.split('/')[-1] | |
if not show_name: | |
show_name = args.root_url.split('/')[-2] | |
parse_and_save(html_parser, full_html, show_name) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Just provide the URL to the Show as the first argument