Python网络编程实战之爬虫技术入门与实践

import requests
 
url = "https://www.example.com"
response = requests.get(url)

html_content = response.text

from bs4 import BeautifulSoup
 
soup = BeautifulSoup(html_content, "html.parser")

title = soup.title.string

import requests
from bs4 import BeautifulSoup
 
url = "https://www.jianshu.com"
response = requests.get(url)
html_content = response.text

import json
 
with open("jianshu_articles.json", "w", encoding="utf-8") as f:
    json.dump(article_info_list, f, ensure_ascii=False, indent=4)

headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3"}
response = requests.get(url, headers=headers)

import time
 
time.sleep(10)

try:
    response = requests.get(url, headers=headers, timeout=5)
    response.raise_for_status()
except requests.exceptions.RequestException as e:
    print(f"Error: {e}")

import requests
from bs4 import BeautifulSoup
import json
import time
 
def fetch_jianshu_articles():
    url = "https://www.jianshu.com"
    headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3"}
 
    try:
        response = requests.get(url, headers=headers, timeout=5)
        response.raise_for_status()
    except requests.exceptions.RequestException as e:
        print(f"Error: {e}")
        return
 
    html_content = response.text
    soup = BeautifulSoup(html_content, "html.parser")
    articles = soup.find_all("div", class_="content")
    article_info_list = []
 
    for article in articles:
        title = article.h2.text.strip()
        author = article.find("span", class_="name").text.strip()
        link = url + article.h2.a["href"]
 
        article_info = {"title": title, "author": author, "link": link}
        article_info_list.append(article_info)
 
    return article_info_list
 
def save_to_json(article_info_list, filename):
    with open(filename, "w", encoding="utf-8") as f:
        json.dump(article_info_list, f, ensure_ascii=False, indent=4)
 
if __name__ == "__main__":
    article_info_list = fetch_jianshu_articles()
    if article_info_list:
        save_to_json(article_info_list, "jianshu_articles.json")
        print("Jianshu articles saved to 'jianshu_articles.json'.")
    else:
        print("Failed to fetch Jianshu articles.")