Kaip nuskaityti norimą svetainės bloką (pirmą):

from bs4 import BeautifulSoup
import requests

r = requests.get("https://www.delfi.lt/")
soup = BeautifulSoup(r.text, 'html.parser')
block = soup.find("article")
print(block.prettify())

Kaip išrinkti norimą informaciją iš bloko:

from bs4 import BeautifulSoup
import requests

r = requests.get("https://www.delfi.lt/")
soup = BeautifulSoup(r.text, 'html.parser')
block = soup.find("article")
category = block.find(class_='headline-labels__label').get_text().strip()
title = block.find(class_='headline-title').a.get_text().strip()
link = block.find(class_='headline-title').a['href']

print(category)
print(title)
print(link)

Kaip gauti visų blokų informaciją:

from bs4 import BeautifulSoup
import requests

r = requests.get("https://www.delfi.lt/")
soup = BeautifulSoup(r.text, 'html.parser')
blocks = soup.find_all("article")
for block in blocks:
    try:
        try:
            category = block.find(class_='headline-labels__label').get_text().strip()
        except:
            category = ""
        title = block.find(class_='headline-title').a.get_text().strip()
        link = block.find(class_='headline-title').a['href']

        if link.startswith("/"):
            link = "https://www.delfi.lt" + link

        print(category)
        print(title)
        print(link)
    except:
        pass

Kaip įrašyti gautą informaciją į csv failą:

from bs4 import BeautifulSoup
import requests
import csv

with open("delfi_naujienos.csv", 'w', encoding="UTF-8", newline="") as file:
    csv_writer = csv.writer(file)
    csv_writer.writerow(["Title", "Category", "Link"])
    r = requests.get("https://www.delfi.lt/")
    soup = BeautifulSoup(r.text, 'html.parser')

    blocks = soup.find_all("article")
    for block in blocks:
        # print(block.prettify())
        try:
            print('-------------------------------------------')
            title = block.find(class_="headline-title").a.get_text().strip()
            try:
                category = block.find(class_="headline-labels__label").get_text().strip()
            except:
                category = ""
            link = block.find(class_="headline-title").a['href']
            if link.startswith("/"):
                link = "https://www.delfi.lt" + link
            print(title)
            print(category)
            print(link)
            csv_writer.writerow([title, category, link])
        except:
            ...

Pavyzdys Nr. 2

Norimo gamintojo parduodamų telefonų išrinkimas iš svetainės

from bs4 import BeautifulSoup
import requests
import csv

r = requests.get("https://www.telia.lt/prekes/telefonai-ir-priedai/mobilieji-telefonai/apple")

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

blocks = soup.find_all(class_='mobiles-product-card card card__product card--anim js-product-compare-product')

with open("telia_apple_telefonai.csv", 'w', encoding="UTF-8", newline="") as file:
    csv_writer = csv.writer(file)
    csv_writer.writerow(["Phone", "Price per Month", "Price"])

    for block in blocks:
        name = block.find(class_="mobiles-product-card__title js-open-product").get_text().strip()
        price_per_month = block.find_all(class_="mobiles-product-card__price-marker")[0].get_text().strip()
        price = block.find_all(class_="mobiles-product-card__price-marker")[1].get_text().strip()
        print(name)
        print(price_per_month)
        print(price)
        csv_writer.writerow([name, price_per_month, price])

Arba iš kelių puslapių, paverčiant viską į skaičius:

from bs4 import BeautifulSoup
import requests
import csv


with open("telia_samsung_telefonai.csv", 'w', encoding="UTF-8", newline="") as file:
    csv_writer = csv.writer(file)
    csv_writer.writerow(["Phone", "Price per Month", "Price"])

    page_num = 1

    while True:
        r = requests.get(f"https://www.telia.lt/prekes/telefonai-ir-priedai/mobilieji-telefonai/samsung?page={page_num}")
        page_num += 1

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

        blocks = soup.find_all(class_='mobiles-product-card card card__product card--anim js-product-compare-product')

        if not blocks:
            print("No more pages")
            break

        for block in blocks:
            name = block.find(class_="mobiles-product-card__title js-open-product").get_text().strip()
            price_per_month = float(block.find_all(class_="mobiles-product-card__price-marker")[0].get_text().strip().split()[0].replace(",", "."))
            price = float(block.find_all(class_="mobiles-product-card__price-marker")[1].get_text().strip().rsplit(maxsplit=1)[0].replace("\xa0", ""))
            print(name)
            print(price_per_month)
            print(price)
            csv_writer.writerow([name, price_per_month, price])

Užduotys

1. Išbandyti šiose skaidrėse aprašytus žingsnius.
2. Nuskaityti aktualius duomenis už norimos svetainės.