手刃爬虫豆瓣

今天学习了爬虫爬取豆瓣电影信息：

import re
import requests
import csv
url = "https://movie.douban.com/top250"
headers = {
    "user-agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3947.100 Safari/537.36"
}
resp = requests.get(url,headers=headers)
a = resp.text
obj = re.compile(r'<li>.*?<div class="item">.*?<span class="title">(?P<name>.*?)</span>.*?<br>(?P<year>.*?)&nbsp.*?'
                 r'<span class="rating_num" property="v:average">(?P<score>.*?)</span>.*?<span>(?P<num>.*?)人评价</span>',re.S)
result = obj.finditer(a)
f=open("abc.csv",mode="w",encoding="utf-8")
csvwriter = csv.writer(f)

for it in result:
    # print(it.group("name"))
    # print(it.group("year").strip())
    # print(it.group("score"))
    # print(it.group("num"))
    dic = it.groupdict()
    dic['year'] = dic['year'].strip()
    csvwriter.writerow(dic.values())
f.close()
print("over")