From 99d2b60d5d78d385bf4f7a1e407e84de02a51c58 Mon Sep 17 00:00:00 2001 From: Karen Zeng Date: Thu, 18 May 2023 15:01:04 -0400 Subject: [PATCH] Modified the main scraping loop --- Multiprocessing.py | 246 ++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 241 insertions(+), 5 deletions(-) diff --git a/Multiprocessing.py b/Multiprocessing.py index b0a035a..901899f 100644 --- a/Multiprocessing.py +++ b/Multiprocessing.py @@ -1,5 +1,20 @@ import multiprocessing import subprocess +import concurrent.futures +from google.cloud import pubsub_v1 +from google.api_core.exceptions import DeadlineExceeded +from selenium import webdriver +from selenium.webdriver.chrome.options import Options +from selenium.webdriver.common.by import By +import json +import time +import os +from concurrent.futures import TimeoutError +import pandas as pd +from selenium.webdriver.support.ui import WebDriverWait +from selenium.webdriver.support import expected_conditions as EC +import selenium.common.exceptions +import re # Define the subset of urls url_list = [ @@ -16,21 +31,242 @@ url_list = [ 'https://www.sayweee.com/en/product/Formosa-Pork-Sung-/23528?trace_id=3c143dd4-4a35-4e8d-93ee-d91f209717e7' ] -# Determine the number of available CPUs -cpu_count = multiprocessing.cpu_count() # Create a pool of worker processes -pool = multiprocessing.Pool(cpu_count) +# pool = multiprocessing.Pool(cpu_count) # Define the function to run the scraper def run_scraper(url): # scraping logic - subprocess.call(['python', 'fp2_13.py', url]) - return run_scraper + df = pd.DataFrame(columns=['Product ID', 'Zip Code', 'Shown Price', 'Minimum Quantity', 'Total Price', 'Unit Price','Sales Count','Sold Status']) + print(f"Created a dataframe: {df}") + options = Options() + options.add_argument('--disable-gpu') + driver = webdriver.Chrome(options=options) + + project_id = "fp-20230425" + subscription_name = "fp-subscription-NFL-zipcodes" + subscriber = pubsub_v1.SubscriberClient() + subscription_path = subscriber.subscription_path(project_id, subscription_name) + + url = 'https://www.sayweee.com/en/product/House-Foods-Firm-Tofu-/85175?trace_id=c93f3d1a-80a4-4e1a-8d41-a402ae43186f' + product_id = url.split("/")[-1][:5] + # product_id = url.split("/")[-1] + driver.delete_all_cookies + driver.get(url) + + def get_element_text(class_name_prefix): + xpath_str = "//*[contains(" # Step 1: search for a class name by matching the beginning of the class name against... + xpath_str += "concat(' ', " # Step 2: a leading space, followed by... + xpath_str += "normalize-space(@class), " # Step 3: the list of class names, separated by single spaces... + xpath_str += "' '), " # Step 4: a trailing space... + xpath_str += f"' {class_name_prefix} ')]" # Step 5: compared against the class name with a single space on either side. + try: + match = driver.find_element(By.XPATH, xpath_str) + return match.get_attribute('textContent') + except selenium.common.exceptions.NoSuchElementException as nsee: + pass + + xpath_str = "//*[contains(" # Step 1: search for a class name by matching the beginning of the class name against... + xpath_str += "concat(' ', " # Step 2: a leading space, followed by... + xpath_str += "normalize-space(@class)), " # Step 3: the list of class names, separated by single spaces... + xpath_str += f"' {class_name_prefix}__')]" # Step 4: compared against the class name prefixed with a single space and ending with two underscores. + try: + match = driver.find_element(By.XPATH, xpath_str) + return match.get_attribute('textContent') + except selenium.common.exceptions.NoSuchElementException as nsee: + pass + return '' + + # Close the cookies setting window + try: + cookie_button = WebDriverWait(driver, 2).until( + EC.presence_of_element_located((By.XPATH, "/html/body/div[3]/div[2]/div/div/div[3]/button")) + ) + print(f"cookie_button = {cookie_button}") + cookie_button.click() + except: + pass + + # Clear any modal dialog + try: + modal_close = WebDriverWait(driver, 2).until( + EC.presence_of_element_located((By.XPATH, "//*[contains(concat(' ', normalize-space(@class), ' '), ' icon-icon-close-s ')]")) + ) + print(f"modal_close = {modal_close}") + modal_close.click() + except: + pass + + # Define callback function for Pub/Sub messages + def callback(message): + # Extract zip code from message data + zip_code = message.message.data.decode('utf-8') + + print(f"Received zip code: {zip_code}") + + try: + try: + # Clear any modal dialog + modal_close = WebDriverWait(driver, 2).until( + EC.presence_of_element_located((By.XPATH, "//*[contains(concat(' ', normalize-space(@class), ' '), ' icon-icon-close-s ')]")) + ) + # print(f"modal_close = {modal_close}") + modal_close.click() + except: + pass + + + try: + + # Clear any notice + notice_close = WebDriverWait(driver, 5).until( + EC.presence_of_element_located((By.XPATH, "/html/body/div[3]/div/div[2]/div/div[2]/div/div/div[1]/div[2]/button"))) + # print(f"notice_close = {notice_close}") + notice_close.click() + except: + pass + + # Enter zip code in the input field and click the "Check" button + zip_button = WebDriverWait(driver, 5).until( + EC.presence_of_element_located((By.XPATH, '/html/body/div[2]/div/header/div[3]/div/div/div[2]/div[1]')) + ) + # print(f"{zip_button:}") + zip_button.click() + + zip_input = WebDriverWait(driver, 2).until( + EC.presence_of_element_located((By.XPATH, '//div/label/following-sibling::input')) + ) + # print(f"{zip_input:}") + zip_input.click() + # print("clearing zip_input") + zip_input.send_keys("\b\b\b\b\b") + # print("sending zip code") + zip_input.send_keys(zip_code) + + check_button = driver.find_element(By.XPATH, "//button[text() = 'Confirm']") + check_button = WebDriverWait(driver, 2).until(EC.presence_of_element_located((By.XPATH,"//button[text() = 'Confirm']"))) + # print(f"{check_button:}") + check_button.click() + # time.sleep(2) + + try: + # Clear any notice + notice_close = WebDriverWait(driver, 2).until(EC.presence_of_element_located((By.XPATH, "/html/body/div[3]/div/div[2]/div/div[2]/div/div/div[1]/div[2]/button"))) + # print(f"notice_close = {notice_close}") + notice_close.click() + except: + pass + + try: + # Clear any modal dialog + modal_close = WebDriverWait(driver, 2).until(EC.presence_of_element_located((By.XPATH, "//*[contains(concat(' ', normalize-space(@class), ' '), ' icon-icon-close-s ')]"))) + # print(f"modal_close = {modal_close}") + modal_close.click() + except: + pass + + # Record sales count, if any + sales_count_element = get_element_text('Header_count') + count_start_index = sales_count_element.index('sold ') + len('sold ') + count_end_index = sales_count_element.index('+') + sales_count = sales_count_element[count_start_index:count_end_index] + # Record any sold status notice + sold_status = get_element_text('UnavailableCartbtn_container') + if sold_status == 'Notify me': + sold_status = 'Sold Out' + + # Extract the price of rice crackers for this zip code + # Check if there is a minimum order quantity + min_quantity: float = 0 + total_price: float = 0 + unit_price: float = 0 + try: + minimum_quantity_str = driver.find_element(By.XPATH, "//div[contains(@class, 'minQuantity')]").get_attribute('innerHTML') + if minimum_quantity_str: + regexp = "Minimum purchase: (\d+) \(\$(\d+\.\d{2}?)" + match = re.search(regexp,minimum_quantity_str) + min_quantity, total_price = match.groups() + except selenium.common.exceptions.NoSuchElementException as nsee: + print("No minimum purhcase string found") + except Exception as e: + print(f"Exception when finding minimum purchase string: {e}") + + ld_json_element = driver.find_element(By.XPATH, "//script[@type='application/ld+json']") + ld_json_text = ld_json_element.get_attribute('innerHTML') + ld_json_start_index = ld_json_text.index('{') + ld_json_end_index = ld_json_text.rindex('}') + 1 + ld_json_json = ld_json_text[ld_json_start_index:ld_json_end_index] + ld_json = json.loads(ld_json_json) + ld_json_price = ld_json['offers']['price'] + # Print the price + print(ld_json_price) + + unit_price_element = driver.find_element(By.XPATH,"//div[contains(@class, 'price_price')]").get_attribute('innerText') + unit_price = unit_price_element.replace("$", "") + print(f"unit_price = {unit_price}" ) + + subscriber.acknowledge(ack_ids = [message.ack_id], subscription = subscription_path) # acknowledge receipt of message + # Append the zip code and price to the dataframe + #append_to_df(zip_code, price) + new_row = pd.DataFrame({'Product ID': [product_id], 'Zip Code': [zip_code], 'Shown Price': [ld_json_price], 'Minimum Quantity': [min_quantity], 'Total Price': [total_price], 'Unit Price': [unit_price], 'Sales Count': [sales_count], 'Sold Status': [sold_status]}) + return pd.concat([df, new_row], ignore_index=True) + #print(f"Recorded the zip code and price: {zip_code},{price}") + #print(f"Updated a dataframe: {df}") + + except Exception as e: + print(f"Caught exception: {e}") + print(f"Price not found for zip code {zip_code}") + price = 'Price not found' + return df + + # Start receiving messages (sync version) + while True: + pull_request = pubsub_v1.types.PullRequest(max_messages = 1, subscription = subscription_path) + messages = [] + try: + pull_response = subscriber.pull(request = pull_request) + messages = pull_response.received_messages + except DeadlineExceeded: + pass + + if messages: + df = callback(messages[0]) + print(f"Updated a dataframe: {df}") + else: + print(f"no messages, trying again at {time.asctime()}") + break + # subprocess.call(['python', 'fp2_13.py', url]) + return df + +if __name__ == '__main__': + # Determine the number of available CPUs + cpu_count = multiprocessing.cpu_count() + + with concurrent.futures.ThreadPoolExecutor(max_workers=cpu_count) as executor: + future_to_url = {executor.submit(run_scraper, url): url for url in url_list} + for future in concurrent.futures.as_completed(future_to_url): + url = future_to_url[future] + try: + result = future.result() + print(f"Scraped data for URL: {url}") + except Exception as e: + print(f"Failed to scrape data for URL: {url}\nError: {e}") + +''' # Run the scraper in parallel for the subset of items results = pool.map(run_scraper, url_list) # Close the pool and wait for the processes to finish pool.close() pool.join() +''' + +for url, result in zip(url_list, result): + # Extract the product ID from the URL + product_id = url.split("/")[-1].split("?")[0] + + # Save the dataframe to the HDF5 file with a unique key + key = f'df_{product_id}' + result.to_hdf('product_data.h5', key=key, mode='a') \ No newline at end of file