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')
# -*- coding: utf-8 -*-
"""
Created on Sun Apr 25 22:30:42 2021
@author: Nikhil Reddy
"""
from autoscraper import AutoScraper
Scrap = AutoScraper()
amzn_url = "https://www.amazon.in/s?k=iphones"
req_list_amzn = ["₹58,400", "New Apple iPhone 11 (128GB) - Black"]
Scrap_amzn = Scrap.build(amzn_url, req_list_amzn)
res_amzn = Scrap.get_result_similar(amzn_url, grouped=True)
dyk = list(res_amzn.keys())
print(dyk)
Scrap.set_rule_aliases({dyk[len(dyk) - 1]: 'Title', dyk[0]: 'Price'})
Scrap.keep_rules([dyk[len(dyk) - 1], dyk[0]])
Scrap.save('amazon-search3')
# -*- coding: utf-8 -*-
"""
Created on Sat Apr 24 12:25:41 2021
@author: win10
"""
from autoscraper import AutoScraper
amazon_url = "https://www.amazon.in/s?k=iphones"
wanted_list = ["₹58,400", "New Apple iPhone 11 (128GB) - Black"]
scraper = AutoScraper()
result = scraper.build(amazon_url, wanted_list)
print(scraper.get_result_similar(amazon_url, grouped=True))
scraper.set_rule_aliases({'rule_io1c': 'Title', 'rule_hm52': 'Price'})
scraper.keep_rules(['rule_io1c', 'rule_hm52'])
scraper.save('AmazonIn-search')
#!/usr/bin/env python
# coding: utf-8
from autoscraper import AutoScraper
amazon_url = "https://www.amazon.in/s?i=aps&k=iphone"
wanted_list = ["New Apple iPhone 12 Pro Max (128GB) - Pacific Blue","₹1,25,900"]
scraper = AutoScraper()
result = scraper.build(amazon_url,wanted_list)
print(scraper.get_result_similar(amazon_url,grouped=True))
scraper.set_rule_aliases({"rule_1943":"Title",
"rule_1gc6":"MRP"})
scraper.keep_rules(["rule_1943","rule_1gc6"])
scraper.save("amazon_search")
"""# Creating scraper object"""
scraper=AutoScraper()
result=scraper.build(amazon_url,wanted_list)
"""# Finding similar data"""
data = scraper.get_result_similar(amazon_url,grouped=True)
print(data)
keys = list(data.keys())
print(keys)
"""# Defining alias"""
scraper.set_rule_aliases({str(keys[0]):'ImageUrl',str(keys[2]):'Title',str(keys[-2]):'Price',str(keys[-1]):'Reviews'})
scraper.save("amazon_in.json")
"""# Testing for other search word"""
amazon_scraper = AutoScraper()
amazon_scraper.load('amazon_in.json')
search = "samsung phones"
amazon_url="https://www.amazon.in/s?k={}&s=price-desc-rank".format(search)
data = amazon_scraper.get_result_similar(amazon_url, group_by_alias=True)
search_data = tuple(zip(data['Title'],data['ImageUrl'],data['Price'],data['Reviews']))
df = pd.DataFrame(columns=['Query','Title','Price','Reviews','ImageUrl'])