今天我们就以猫眼为例
import requests,re
#代理ip
proxy={
"HTTP": "113.3.152.88:8118",
"HTTPS":"219.234.5.128:3128",
}
#爬取网址
url="https://maoyan.com/board"
#伪装头
headers={
"User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko)Chrome/70.0.3538.110 Safari/537.36",
}
#接收返回对象
response=requests.get(url,headers=headers,proxies=proxy)
#utf8解码
html=response.content.decode("utf-8")
#正则提取数据 可以用xpath bs4提取
ret=re.compile(r'<dd>[\w\W]*?<i class="board-index board-index-(\d{1,2})">\d{1,2}</i>[\w\W]*?<img data-src="(.*?)" alt="(.*?)"[\w\W]*?<p class="star">\s*?(.*?)\s*?</p>[\w\W]*?<p class="releasetime">(.*?)</p>[\w\W]*?<i class="integer">(.*?)</i>.*?class="fraction">(.*?)</i>',re.S)
res=ret.findall(html)
for i in res:
print("电影:",i[2])
print("电影图片:",i[1])
print("主演:",i[3].strip())
print(i[4])
print("排名:", i[0])
print("评分:",i[-2]+i[-1])
print()
这次代码比较简单,如果看不懂的,可以翻看我之前的写的博客!