python3学习之路 -- 9.1.3）- 获取豆瓣top250_变量

# 拿到页面源代码  requests
# 通过re提取想要的信息  re
import requests
import re
import csv

# 获取多页数据，https://movie.douban.com/top250 这个地址每25是一页
start = input("输入想从哪个数字+1开始获取25条信息：")
url = f"https://movie.douban.com/top250?start={start}"
#print(url) https://movie.douban.com/top250?start=25

header = {
    "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/101.0.4951.54 Safari/537.36"
}

data = {
    "ht": "true"
}

resp = requests.get(url, headers=header, data=data)
page_content = resp.text
#print(page_content)

# 解析数据
obj = re.compile(r'<li>.*?<div class="item">.*?<span class="title">(?P<title>.*?)</span>.*?'
                 r'<p class="">.*?<br>(?P<year>.*?)&nbsp.*?<span class="rating_num" '
                 r'property="v:average">(?P<pingfen>.*?)</span>'
                 r'.*?<span>(?P<pingjia>.*?)人评价', re.S)

# 开始匹配，并将存到文件 格式类似： 肖申克的救赎,1994,9.7,2615095
result = obj.finditer(page_content)
f = open("02_2_douban.csv", "w", encoding="UTF-8", newline="")
csvwriter = csv.writer(f)
for i in result:
    # 将数据放到字典
    dic = i.groupdict()
    dic['year'] = dic['year'].strip()
    csvwriter.writerow(dic.values())

f.close()
print("over!")