PythonでeBayをスクレイピングして価格を監視する方法

mkdir ebay-scraper

cd ebay-scraper

python -m venv env

print('Hello, World!')

python scraper.py

Hello, World!

pip install beautifulsoup4 requests

import requests

from bs4 import BeautifulSoup

# scraping logic...

https://www.ebay.com/itm/<ITM_ID>

https://www.ebay.com/itm/225605642071?epid=26057553242&hash=item348724e757:g:~ykAAOSw201kD1un&amdata=enc%3AAQAIAAAA4OMICjL%2BH6HBrWqJLiCPpCurGf8qKkO7CuQwOkJClqK%2BT2B5ioN3Z9pwm4r7tGSGG%2FI31uN6k0IJr0SEMEkSYRrz1de9XKIfQhatgKQJzIU6B9GnR6ZYbzcU8AGyKT6iUTEkJWkOicfCYI5N0qWL8gYV2RGT4zr6cCkJQnmuYIjhzFonqwFVdYKYukhWNWVrlcv5g%2BI9kitSz8k%2F8eqAz7IzcdGE44xsEaSU2yz%2BJxneYq0PHoJoVt%2FBujuSnmnO1AXqjGamS3tgNcK5Tqu36QhHRB0tiwUfAMrzLCOe9zTa%7Ctkp%3ABFBMmNDJgZJi

import requests

from bs4 import BeautifulSoup

import sys

# if there are no CLI parameters

if len(sys.argv) <= 1:

    print('Item ID argument missing!')

    sys.exit(2)

# read the item ID from a CLI argument

item_id = sys.argv[1]

# build the URL of the target product page

url = f'https://www.ebay.com/itm/{item_id}'

# scraping logic...

Assume you want to scrape the product 225605642071. You can launch your scraper with:

python scraper.py 225605642071

Item ID argument missing!

https://www.ebay.com/itm/225605642071

page = requests.get(url)

soup = BeautifulSoup(page.text, 'html.parser')

item = {}

.x-price-primary span[itemprop="price"]

And the currency with:

.x-price-primary span[itemprop="priceCurrency"]

Apply those selectors in Beautiful Soup and retrieve the desired data with:

price_html_element = soup.select_one('.x-price-primary span[itemprop="price"]')

price = price_html_element['content']

currency_html_element = soup.select_one('.x-price-primary span[itemprop="priceCurrency"]')

currency = currency_html_element['content']

label_html_elements = soup.select('.ux-labels-values__labels')

for label_html_element in label_html_elements:

    if 'Shipping:' in label_html_element.text:

        shipping_price_html_element = label_html_element.next_sibling.select_one('.ux-textspans--BOLD')

        # if there is a shipping price HTML element

        if shipping_price_html_element is not None:

            # extract the float number of the price from

            # the text content

            shipping_price = re.findall("\d+[.,]\d+", shipping_price_html_element.text)[0]

        break

US $105.44

import re

Add the collected data to the item dictionary:

item['price'] = price

item['shipping_price'] = shipping_price

item['currency'] = currency

Print it with:

print(item)

And you will get:

{'price': '499.99', 'shipping_price': '72.58', 'currency': 'USD'}

section_title_elements = soup.select('.section-title')

for section_title_element in section_title_elements:

    if 'Item specifics' in section_title_element.text or 'About this product' in section_title_element.text:

        # get the parent element containing the entire section

        section_element = section_title_element.parent

        for section_col in section_element.select('.ux-layout-section-evo__col'):

            print(section_col.text)

            col_label = section_col.select_one('.ux-labels-values__labels')

            col_value = section_col.select_one('.ux-labels-values__values')

            # if both elements are present

            if col_label is not None and col_value is not None:

                item[col_label.text] = col_value.text

{'price': '499.99', 'shipping_price': '72.58', 'currency': 'USD', 'Condition': "New: A brand-new, unused, unopened, undamaged item in its original packaging (where packaging is applicable). Packaging should be the same as what is found in a retail store, unless the item is handmade or was packaged by the manufacturer in non-retail packaging, such as an unprinted box or plastic bag. See the seller's listing for full details. See all condition definitionsopens in a new window or tab ", 'Manufacturer Warranty': '1 Year', 'Item Height': '16.89"', 'Item Length': '18.5"', 'Item Depth': '6.94"', 'Item Weight': '15.17 lbs', 'UPC': '0711719558255', 'Brand': 'Sony', 'Type': 'Home Console', 'Region Code': 'Region Free', 'Platform': 'Sony PlayStation 5', 'Color': 'White', 'Model': 'Sony PlayStation 5 Blu-Ray Edition', 'Connectivity': 'HDMI', 'MPN': '1000032624', 'Features': '3D Audio Technology, Blu-Ray Compatible, Wi-Fi Capability, Internet Browsing', 'Storage Capacity': '825 GB', 'Resolution': '4K (UHD)', 'eBay Product ID (ePID)': '26057553242', 'Manufacturer Color': 'White', 'Edition': 'God of War Ragnarök Bundle', 'Release Year': '2022'}

import json

# scraping logic...

with open('product_info.json', 'w') as file:

    json.dump(item, file)

import requests

from bs4 import BeautifulSoup

import sys

import re

import json

# if there are no CLI parameters

if len(sys.argv) <= 1:

    print('Item ID argument missing!')

    sys.exit(2)

# read the item ID from a CLI argument

item_id = sys.argv[1]

# build the URL of the target product page

url = f'https://www.ebay.com/itm/{item_id}'

# download the target page

page = requests.get(url)

# parse the HTML document returned by the server

soup = BeautifulSoup(page.text, 'html.parser')

# initialize the object that will contain

# the scraped data

item = {}

# price scraping logic

price_html_element = soup.select_one('.x-price-primary span[itemprop="price"]')

price = price_html_element['content']

currency_html_element = soup.select_one('.x-price-primary span[itemprop="priceCurrency"]')

currency = currency_html_element['content']

shipping_price = None

label_html_elements = soup.select('.ux-labels-values__labels')

for label_html_element in label_html_elements:

    if 'Shipping:' in label_html_element.text:

        shipping_price_html_element = label_html_element.next_sibling.select_one('.ux-textspans--BOLD')

        # if there is not a shipping price HTML element

        if shipping_price_html_element is not None:

            # extract the float number of the price from

            # the text content

            shipping_price = re.findall("\d+[.,]\d+", shipping_price_html_element.text)[0]

        break

item['price'] = price

item['shipping_price'] = shipping_price

item['currency'] = currency

# product detail scraping logic

section_title_elements = soup.select('.section-title')

for section_title_element in section_title_elements:

    if 'Item specifics' in section_title_element.text or 'About this product' in section_title_element.text:

        # get the parent element containing the entire section

        section_element = section_title_element.parent

        for section_col in section_element.select('.ux-layout-section-evo__col'):

            print(section_col.text)

            col_label = section_col.select_one('.ux-labels-values__labels')

            col_value = section_col.select_one('.ux-labels-values__values')

            # if both elements are present

            if col_label is not None and col_value is not None:

                item[col_label.text] = col_value.text

# export the scraped data to a JSON file

with open('product_info.json', 'w') as file:

    json.dump(item, file, indent=4)

python scraper.py 225605642071

{

    "price": "499.99",

    "shipping_price": "72.58",

    "currency": "USD",

    "Condition": "New: A brand-new, unused, unopened, undamaged item in its original packaging (where packaging is applicable). Packaging should be the same as what is found in a retail store, unless the item is handmade or was packaged by the manufacturer in non-retail packaging, such as an unprinted box or plastic bag. See the seller's listing for full details",

    "Manufacturer Warranty": "1 Year",

    "Item Height": "16.89\"",

    "Item Length": "18.5\"",

    "Item Depth": "6.94\"",

    "Item Weight": "15.17 lbs",

    "UPC": "0711719558255",

    "Brand": "Sony",

    "Type": "Home Console",

    "Region Code": "Region Free",

    "Platform": "Sony PlayStation 5",

    "Color": "White",

    "Model": "Sony PlayStation 5 Blu-Ray Edition",

    "Connectivity": "HDMI",

    "MPN": "1000032624",

    "Features": "3D Audio Technology, Blu-Ray Compatible, Wi-Fi Capability, Internet Browsing",

    "Storage Capacity": "825 GB",

    "Resolution": "4K (UHD)",

    "eBay Product ID (ePID)": "26057553242",

    "Manufacturer Color": "White",

    "Edition": "God of War Ragnarok Bundle",

    "Release Year": "2022"

}