import requests from bs4 import BeautifulSoup import csv # 发送HTTP请求获取网页内容 url = "https://item.jd.com/100016034394.html" # 替换为目标商品评价页面的URL response = requests.get(url) html = response.text # 使用BeautifulSoup解析网页内容 soup = BeautifulSoup(html, "html.parser") # 获取所有评价信息 comments = soup.find_all("div", class_="comment-item") # 创建CSV文件并写入数据 filename = "商品评价.csv" with open(filename, "w", encoding="utf-8-sig", newline="") as csvfile: writer = csv.writer(csvfile) writer.writerow(["用户", "评分", "评价内容"]) # 写入表头 # 写入每条评价的数据 for comment in comments: user = comment.find("div", class_="user-info").find("span").text.strip() rating = comment.find("div", class_="comment-star").find("i")["class"][1].split("-")[1] content = comment.find("div", class_="comment-con").find("p").text.strip() writer.writerow([user, rating, content]) print(f"成功爬取并保存为 {filename}") 上述代码加入用户代理内容怎么加
时间: 2023-12-05 11:45:19 浏览: 54
你可以在发送HTTP请求时,通过设置headers参数来添加用户代理内容。可以使用`User-Agent`字段来设置用户代理。以下是修改后的代码示例:
```python
import requests
from bs4 import BeautifulSoup
import csv
# 发送HTTP请求获取网页内容
url = "https://item.jd.com/100016034394.html" # 替换为目标商品评价页面的URL
# 设置用户代理
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.81 Safari/537.36"
}
response = requests.get(url, headers=headers)
html = response.text
# 使用BeautifulSoup解析网页内容
soup = BeautifulSoup(html, "html.parser")
# 获取所有评价信息
comments = soup.find_all("div", class_="comment-item")
# 创建CSV文件并写入数据
filename = "商品评价.csv"
with open(filename, "w", encoding="utf-8-sig", newline="") as csvfile:
writer = csv.writer(csvfile)
writer.writerow(["用户", "评分", "评价内容"]) # 写入表头
# 写入每条评价的数据
for comment in comments:
user = comment.find("div", class_="user-info").find("span").text.strip()
rating = comment.find("div", class_="comment-star").find("i")["class"][1].split("-")[1]
content = comment.find("div", class_="comment-con").find("p").text.strip()
writer.writerow([user, rating, content])
print(f"成功爬取并保存为 {filename}")
```
在上述代码中,我们在发送请求前设置了`headers`参数,并且将用户代理信息添加到其中。你可以根据需要修改`User-Agent`字段的值。