def autoscraper(Link=None, Metodo=None): url = request.args["Link"] link = request.args["Link"] Metodo = request.args["Metodo"] wanted_list = [Metodo] scraper = AutoScraper() scraper.build(link, wanted_list) dict = scraper.get_result_exact(link, unique=False, grouped=True) l = [] [l.extend([k, v]) for k, v in dict.items()] regla = l[0] scraper.set_rule_aliases({regla: 'regla'}) scraper.keep_rules([regla]) url = url.replace("http:", "").replace("//", "").replace(".", "").replace( "www", "").replace("https:", "").replace("/", "").replace("\n", "").replace("-", "") scraper.save(url + '-search') data = get_pagina_result(url, link) json_format = json.dumps(data, indent=4, separators=(',', ': '), sort_keys=True, ensure_ascii=False) return json_format
from autoscraper import AutoScraper url = 'https://www.rosario3.com/' wanted_list = [ "/especiales/Club-de-Lectura-Brandon-Sanderson-es-mejor-que-J.-R.-R.-Tolkien-20200909-0043.html" ] scraper = AutoScraper() result = scraper.build(url, wanted_list) dict = scraper.get_result_exact(url, unique=False, grouped=True) l = [] [l.extend([k, v]) for k, v in dict.items()] regla = l[0] scraper.set_rule_aliases({regla: 'regla'}) scraper.keep_rules([regla]) scraper.save('rosario3-search')