Beautiful Soup을 사용하여 공개 웹에서 데이터를 추출하는 방법

#Install Beautiful Soup using pip.
pip install beautifulsoup4 lxml

import requests
from bs4 import BeautifulSoup

base_url = 'https://example-blog.com/page/'
page_number = 1
all_titles = []

while True:
    # Construct the URL for the current page
    url = f'{base_url}{page_number}'
    response = requests.get(url)
    soup = BeautifulSoup(response.content, 'html.parser')

    # Find all article titles on the current page
    titles = soup.find_all('h2', class_='article-title')
    if not titles:
        break  # Exit the loop if no titles are found (end of pagination)

    # Extract and store the titles
    for title in titles:
        all_titles.append(title.get_text())

    # Move to the next page
    page_number += 1

# Print all collected titles
for title in all_titles:
    print(title)

import requests
from bs4 import BeautifulSoup

url = 'https://example-blog.com/post/123'
response = requests.get(url)
soup = BeautifulSoup(response.content, 'html.parser')

# Find the comments section
comments_section = soup.find('div', class_='comments')

# Extract individual comments
comments = comments_section.find_all('div', class_='comment')

for comment in comments:
    # Extract author and content from each comment
    author = comment.find('span', class_='author').get_text()
    content = comment.find('p', class_='content').get_text()
    print(f'Author: {author}\nContent: {content}\n')

import requests
from bs4 import BeautifulSoup

# URL to the API endpoint providing the AJAX data
ajax_url = 'https://example.com/api/data?page=1'
response = requests.get(ajax_url)
data = response.json()

# Extract and print data from the JSON response
for item in data['results']:
    print(item['field1'], item['field2'])