Created
December 20, 2018 13:58
-
-
Save lobstrio/22d2d15723df7c478377d12376f60902 to your computer and use it in GitHub Desktop.
Web Scraping Python Script for the Xmas Deals on Amazon using Requests
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
# -*- coding: utf-8 -*- | |
# Copyright(C) 2018 Sasha Bouloudnine | |
import requests | |
import sys | |
import re | |
import ast | |
import json | |
import time | |
import csv | |
class AmazonXmasExtract: | |
def __init__(self, node, write=None): | |
self.node = node | |
self.write = write | |
self.s = requests.Session() | |
self.s.headers['User-Agent'] = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_6_8) AppleWebKit/537.13+ (KHTML, like Gecko) Version/5.1.7 Safari/534.57.2' | |
def extract(self): | |
# extract home_page | |
base_url = 'https://www.amazon.fr/b/ref=sd_allcat_xmasgno?ie=UTF8&node={}'.format(self.node) | |
response = self.s.get(base_url) | |
if response.status_code == 200: | |
pass | |
else: | |
print(response.text) | |
sys.exit() | |
# extract list_of_ids | |
pattern = r'(?<="sortedDealIDs"\s:\s)[^\]]+\]' | |
list_offers_id = ast.literal_eval(re.findall(pattern, response.text)[0]) | |
print('LIST OFFER ID: {}'.format(list_offers_id)) | |
assert isinstance(list_offers_id, list) | |
# extract amazon marketplace id | |
pattern = r'(?<=ue_mid = \')\w+' | |
mid = re.findall(pattern, response.text)[0] | |
print('MID: {}'.format(mid)) | |
# extract session_id | |
session_id = self.s.cookies.values()[0] | |
print('SESSION ID: {}'.format(session_id)) | |
# build json for post request | |
result_list = [] | |
sublists = [list_offers_id[i:i+5] for i in range(0, len(list_offers_id), 5)] | |
for sublist in sublists: | |
list_for_json = [] | |
for deal_id in sublist: | |
print(deal_id) | |
deal_id_dict = {'dealID': deal_id} | |
list_for_json.append(deal_id_dict) | |
json_to_post = { | |
'requestMetadata': | |
{ | |
'marketplaceID': mid, | |
'clientID': 'goldbox_mobile_pc', | |
'sessionID': session_id | |
}, | |
'dealTargets': list_for_json, | |
'responseSize': 'STATUS_ONLY', | |
'itemResponseSize': 'DEFAULT_WITH_PREEMPTIVE_LEAKING' | |
} | |
json_to_post = json.dumps(json_to_post) | |
# post request | |
nodecache_value = str(time.time()).replace('.', '')[:13] | |
url = 'https://www.amazon.fr/xa/dealcontent/v2/GetDeals?nocache={}'.format(nodecache_value) | |
response = json.loads(self.s.post(url=url, data=json_to_post).text) | |
time.sleep(1) # cool pause | |
for key in response['dealDetails'].keys(): | |
deal_details_dict = response['dealDetails'][key] | |
result_list.append(deal_details_dict) | |
# write csv | |
if self.write: | |
with open('/Users/sashabouloudnine/Desktop/amazon_deals.csv', mode='w') as f: | |
writer = csv.DictWriter(f, delimiter='\t', fieldnames=result_list[0].keys()) | |
writer.writeheader() | |
for deal_details_dict in result_list: | |
writer.writerow(deal_details_dict) | |
if __name__ == '__main__': | |
my = AmazonXmasExtract(node='2155235031', write=True) | |
my.extract() | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment