目的
猫眼视频Top100电影榜单
源码
#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Author : jia666
# @Time : 2020/08/28 9:57
import re
import requests
class TOP_100(object):
def __init__(self):
self.sec = requests.session()
self.sec.headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.116 Safari/537.36",
}
self.main() #主逻辑
def get_one_page(self, url):
# 异常处理
try:
# 发送请求
response = self.sec.get(url)
self.sec.close()
# 判断网页状态码是否成功获取网页
if response.status_code == 200:
return response.text
return None
except Exception:
# 其他返回None
return None
def parse_one_page(self,html):
# print(html)
# 利用正则表达式进行信息过滤
self.rank_numm=re.findall('<i class="rank-number" data-reactid=".*?">(.*?)<\/i>',html,re.S)
self.title_name = re.findall('<h3 class="title" data-reactid=".*?">(.*?)<\/h3>', html, re.S)
self.actors = re.findall('<div class="actors" data-reactid=".*?">(.*?)<\/div>', html, re.S)
self.date = re.findall('<div class="date" data-reactid=".*?">(.*?)<\/div>', html, re.S)[1:]
self.score = re.findall('<span class="number" data-reactid=".*?">(.*?)<\/span>', html, re.S)
def write_to_file(self):
# 写入信息
with open("猫眼电影Top100.txt", 'a+', encoding='utf-8') as f:
for i in range(len(self.rank_numm)):
# 格式整理
item = "排名" + ":" + self.rank_numm[i] + '\n' + \
"电影名称" + ':' + self.title_name[i] + '\n' + \
"演员" + ':' + self.actors[i] + '\n' + \
"上映时间" + ':' + self.date[i] + '\n' + \
"评分" + ':' + self.score[i] + '\n\n'
# 写入
f.write(str(item) + '\n')
# 关闭
f.close()
def main(self):
# 设置UA,模拟浏览器
# 生成url
url = 'https://m.maoyan.com/board/4'
# 获取返回的网页
html = self.get_one_page(url)
# 解析网页,进行信息筛选
items = self.parse_one_page(html)
# 信息写入
self.write_to_file()
if __name__ == '__main__':
print("开始抓取猫眼TOP100电影榜单................")
TOP_100()
print("猫眼TOP100电影榜单写入完成................")
效果如下