Das deutsche Python-Forum

Code: Alles auswählen

import bs4
from urllib.request import urlopen
from bs4 import BeautifulSoup as soup

my_url = 'https://www.newegg.com/Video-Cards-Video-Devices/Category/ID-38?Tpk=graphics%20card'

# opening url and grabbing the web page
uClient = urlopen(my_url)
page_html = uClient.read()
uClient.close()

# html parsing
page_soup = soup(page_html, 'html.parser')

# grabbing all containers with class name = item-container
containers = page_soup.findAll('div', {'class':'item-container'})

filename = "products.csv"
f = open(filename, 'w')

headers = "brands, product_name, shipping\n"

f.write(headers)

container = containers[1]

for container in containers:
    brand = container.div.div.a.img['title']
    title_container = container.findAll('a', {'class':'item-title'})
    product_name = title_container[0].text
    ship_container = container.findAll('li', {'class':'price-ship'})
    # use strip() to remove blank spaces before and after text
    shipping = ship_container[0].text.strip()

    print("brand:" + brand)
    print("product_name:" + product_name)
    print("shipping:" + shipping)

    f.write(brand + ',' + product_name.replace(',' , '|') + ',' + shipping + '\n')

f.close()

Code: Alles auswählen

import bs4
from urllib.request import urlopen
from bs4 import BeautifulSoup as soup
import csv

START_URL = 'https://www.obi.de/search/elektrowerkzeuge/'


def load_site(url):
    """Lädt die Url und gibt einen Html-Text zurück."""
    uClient = urlopen(url)
    page_html = uClient.read()
    uClient.close()
    return soup(page_html, 'html.parser')


# Wieviele weiterführende Seiten gibt es?
start_soup = load_site(START_URL)
site_count = start_soup.find("a", class_="pagination-bar__link-refs js-pagination-link-refs").text.split()[-1]


produkt_counter = 0
with open("products.csv", "w") as file:
    writer = csv.DictWriter(file, fieldnames=["titel", "marke", "preis"])
    writer.writeheader()
    for count in range(1, int(site_count) + 1):
        page_soup = load_site(f"https://www.obi.de/search/elektrowerkzeuge/?page={count}")
        produkte = page_soup.find_all("a", class_="product-wrapper wt_ignore")
        for product in produkte:
            produkt_counter += 1
            print(f"Gefundener Artikel Nr.{produkt_counter}:")
            titel = product.find('span', class_='description').text
            print(f"Titel: {titel}")
            marke = titel.split()[0]
            print(f"Marke: {marke}")
            preis = product.find(class_='price-new')['data-csscontent']
            print(f"Preis: {preis}\n")
            writer.writerow({"titel": titel, "marke": marke, "preis": preis})