&
[root@xxn maoyan]# cat cat.py
#!/usr/bin/env python
#coding:utf-8
import requests
from bs4 import BeautifulSoup
def movieurl(url):
"""
用来获取电影的单页url地址
"""
headers = {
"User-Agent":"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 UBrowser/6.2.3964.2 Safari/537.36",
}
response = requests.get(url,headers=headers,timeout=10)
soup= BeautifulSoup(response.text,'lxml')
href = soup.find_all('div',class_="channel-detail movie-item-title")[0]
movieurl = "http://maoyan.com%s" % href.find('a')['href']
return movieurl
def moveinfo(url):
"""
得到电影的中文名,票房单位。
如果票房单位没数据,说明票房"暂无"。
"""
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 UBrowser/6.2.3964.2 Safari/537.36",
}
response = requests.get(url, headers=headers,timeout=5)
soup = BeautifulSoup(response.text, 'lxml')
C