import requests
import re
from time import sleep
# 目标电影网;https://nnyy.best/ ,爬取电影名字做测试。
res = requests.session()
headers = {
'authority': 'nnyy.best',
'cache-control': 'max-age=0',
'upgrade-insecure-requests': '1',
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36',
'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
'sec-fetch-site': 'same-origin',
'sec-fetch-mode': 'navigate',
'sec-fetch-user': '?1',
'sec-fetch-dest': 'document',
'referer': 'https://nnyy.best/dianying?page=2',
'accept-language': 'zh-CN,zh;q=0.9',
}
for j in range(1,11):
params = {
'page': j,
}
print(f"爬取第{j}页")
response = res.get('https://nnyy.best/dianying', params=params, headers=headers)
data = response.text
# data_text = re.findall(r'<a href="/movie/.*?truncate group-hover:.*?text-center">(.*?)</a>',data,re.S)
data_text = re.findall(r'<a href="/movie/.*?\[#ec2d7a] text-center">(.*?)</a>', data, re.S)
for i in data_text:
print(i)
sleep(3)
标签：nnyy,提取,正则表达式,text,09,re,sec,data,best From： https://www.cnblogs.com/chenzhi2023/p/17603059.html