functions.py

#%%
from selectorlib import Extractor
import requests 
import json 
from time import sleep
import random
import json
import re

user_agent_list = [
    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_5) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/13.1.1 Safari/605.1.15',
    'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:77.0) Gecko/20100101 Firefox/77.0',
    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36',
    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.15; rv:77.0) Gecko/20100101 Firefox/77.0',
    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36',
]
#%%
# Create an Extractor by reading from the YAML file
e = Extractor.from_yaml_file('search_results.yml')

def scrape(url):  

    headers = {
        'dnt': '1',
        'upgrade-insecure-requests': '1',
        'user-agent': random.choice(user_agent_list),
        'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
        'sec-fetch-site': 'same-origin',
        'sec-fetch-mode': 'navigate',
        'sec-fetch-user': '?1',
        'sec-fetch-dest': 'document',
        'referer': 'https://www.amazon.com/',
        'accept-language': 'en-GB,en-US;q=0.9,en;q=0.8',
    }

    # Download the page using requests
    print("Downloading %s"%url)
    r = requests.get(url, headers=headers)
    # Simple check to check if page was blocked (Usually 503)
    if r.status_code > 500:
        if "To discuss automated access to Amazon data please contact" in r.text:
            print("Page %s was blocked by Amazon. Please try using better proxies\n"%url)
        else:
            print("Page %s must have been blocked by Amazon as the status code was %d"%(url,r.status_code))
        return None
    # Pass the HTML of the page and create 
    return e.extract(r.text)

#%%
# product_data = []

    
#%%
def load_jsonl(input_path) -> list:
    with open("search_results_urls.txt",'r') as urllist, open('search_results_output.jsonl','w') as outfile:
        for url in urllist.read().splitlines():
            data = scrape(url) 
            if data:
                for product in data['products']:
                    product['search_url'] = url
                    print("Saving Product: %s"%product['title'])
                    json.dump(product,outfile)
                    outfile.write("\n")
                    #sleep(1)
    """
    Read list of objects from a JSON lines file.
    """
    data = []
    with open(input_path, 'r', encoding='utf-8') as f:
        for line in f:
            data.append(json.loads(line.rstrip('\n|\r')))
    print('Loaded {} records from {}'.format(len(data), input_path))
    return data


def pattern_searcher(search_str:str, search_list:str):

    search_obj = re.search(search_list, search_str)
    if search_obj :
        return_str = search_str[search_obj.start(): search_obj.end()]
    else:
        return_str = 'NA'
    return return_str