用于网络抓取的 HTML 选择器指南

import requests
from bs4 import BeautifulSoup
# Step 1: Send a GET request to the website
url = "https://www.scrapethissite.com/pages/"
response = requests.get(url)
if response.status_code == 200:
   # Step 2: Parse the HTML content with BeautifulSoup
   soup = BeautifulSoup(response.text, 'html.parser')
  
   # Step 3: Find the div with id="pages"
   pages_div = soup.find("div", id="pages")
  
   # Step 4: Display the content or handle it as needed
   if pages_div:
       print("Content of the div with id='pages':")
       print(pages_div.text.strip())
   else:
       print("No div with id='pages' found.")
else:
   print(f"Failed to retrieve the webpage. Status code: {response.status_code}")

import requests
from bs4 import BeautifulSoup
# Step 1: Send a GET request to the website
url = "https://www.scrapethissite.com/pages/"
response = requests.get(url)
if response.status_code == 200:
   # Step 2: Parse the HTML content with BeautifulSoup
   soup = BeautifulSoup(response.text, 'html.parser')
  
   # Step 3: Find all elements with class="page"
   page_elements = soup.find_all("div", class_="page")
  
   # Step 4: Save each element's text content in a list
   pages_list = [page.text.strip() for page in page_elements]
  
   print("Content of elements with class 'page':")
   for i, page in enumerate(pages_list, start=1):
       print(f"Page {i}:")
       print(page)
       print("-" * 20)
else:
   print(f"Failed to retrieve the webpage. Status code: {response.status_code}")

import requests
from bs4 import BeautifulSoup
# Step 1: Send a GET request to the website
url = "https://www.scrapethissite.com/pages/frames/"
response = requests.get(url)
if response.status_code == 200:
   # Step 2: Parse the HTML content with BeautifulSoup
   soup = BeautifulSoup(response.text, 'html.parser')
  
   # Step 3: Find all <img> elements with a 'src' attribute
   image_elements = soup.find_all("img", src=True)
  
   # Step 4: Save the 'src' attributes in a list
   images_list = [img['src'] for img in image_elements]
  
   print("Image sources found on the page:")
   for i, src in enumerate(images_list, start=1):
       print(f"Image {i}: {src}")
else:
   print(f"Failed to retrieve the webpage. Status code: {response.status_code}")

import requests
from bs4 import BeautifulSoup

url = "https://www.scrapethissite.com/pages/forms/"

# Step 1: Send a GET request to the website
response = requests.get(url)

if response.status_code == 200:
   # Step 2: Parse the HTML content with BeautifulSoup
   soup = BeautifulSoup(response.text, 'html.parser')
  
   # Step 3: Find all rows in the table with class="team"
   teams_data = []
   team_rows = soup.find_all("tr", class_="team")
  
   # Step 4: Extract and store each team's data
   for row in team_rows:
       team = {
           "name": row.find("td", class_="name").text.strip(),
           "year": row.find("td", class_="year").text.strip(),
           "wins": row.find("td", class_="wins").text.strip(),
           "losses": row.find("td", class_="losses").text.strip(),
           "ot_losses": row.find("td", class_="ot-losses").text.strip(),
           "win_pct": row.find("td", class_="pct").text.strip(),
           "goals_for": row.find("td", class_="gf").text.strip(),
           "goals_against": row.find("td", class_="ga").text.strip(),
           "goal_diff": row.find("td", class_="diff").text.strip(),
       }
       teams_data.append(team)
  
   # Step 5: Display the extracted data
   for team in teams_data:
       print(team)
else:
   print(f"Failed to retrieve the webpage. Status code: {response.status_code}")

import requests
from bs4 import BeautifulSoup
# Target URL
url = "https://www.scrapethissite.com/pages/"
response = requests.get(url)
if response.status_code == 200:
   # Step 2: Parse the HTML content with BeautifulSoup
   soup = BeautifulSoup(response.text, 'html.parser')
  
   # Use ID selector to find the main content
   main_content = soup.find(id="pages")
  
   # Use class selector to find each "page" section
   pages = main_content.find_all("div", class_="page") if main_content else []
  
   # Extract details from each "page" section using hierarchical selectors
   for page in pages:
       # Use hierarchical selector to find title link and URL within each "page"
       title_tag = page.find("h3", class_="page-title")
       title = title_tag.text.strip() if title_tag else "No Title"
       link = title_tag.find("a")["href"] if title_tag and title_tag.find("a") else "No Link"
      
       # Use class selector to find the description
       description = page.find("p", class_="lead session-desc").text.strip() if page.find("p", class_="lead session-desc") else "No Description"
      
       print(f"Title: {title}")
       print(f"Link: {link}")
       print(f"Description: {description}")
       print("-" * 40)
else:
   print(f"Failed to retrieve the webpage. Status code: {response.status_code}")