[计算机头歌]爬虫进阶

第1关：单网页爬取

import urllib.request
import csv
import re

# 打开京东，读取并爬到内存中，解码, 并赋值给data
# 将data保存到本地
# ********** Begin ********** #
url = 'http://www.jd.com'
response = urllib.request.urlopen(url)
data = response.read().decode('utf-8')

# 保存网页到本地文件
with open('./step1/京东.html', 'w', encoding='utf-8') as file:
    file.write(data)
# ********** End ********** #

# 使用正则提取title
# 保存数据到csv文件中
# ********** Begin ********** #
title_pattern = re.compile(r'<title>(.*?)</title>')
title_match = title_pattern.search(data)
title = title_match.group(1) if title_match else 'Title not found'

# 保存title到CSV文件
with open('./step1/csv_file.csv', 'w', newline='', encoding='utf-8') as csvfile:
    csvwriter = csv.writer(csvfile)
    csvwriter.writerow(['Title'