爬虫--人人网-简易爬取

from Day1.tuozhan_all import get

# 0. url
url = 'http://www.renren.com/966927992'
# 1. 构造headers
headers = {
    #'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
    #'Accept-Encoding': 'gzip, deflate',
    #'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8',
    #'Cache-Control': 'max-age=0',
    #'Connection': 'keep-alive',
    'Cookie': 'anonymid=jkt0b8ab-q2jf6z; depovince=GW; _r01_=1; JSESSIONID=abcGJgLjV4-TIaBij_1uw; ick_login=9064892c-3ad2-43ae-b884-ed4ebbab6249; jebecookies=868d7d34-c453-40ee-93e8-197b43bdc86a|||||; _de=B996A2060AAF2DDA74DFAFD510163D3F; p=c48fa2c085eb307ad984daa9625fe72b2; first_login_flag=1; ln_uact=18510556963; ln_hurl=http://head.xiaonei.com/photos/0/0/men_main.gif; t=41d3adf9f7f90cd5b1d7bcfd4e3daf3b2; societyguester=41d3adf9f7f90cd5b1d7bcfd4e3daf3b2; id=966927992; xnsid=c97d475f; ver=7.0; loginfrom=null; jebe_key=a34f3f96-cded-4ab0-b18b-def8f814944a%7C65e0c5286f0503e29e3484234097e54d%7C1534217862022%7C1%7C1534217873290; wp_fold=0',
    #'Host': 'www.renren.com',
    #'Referer': 'http://renren.com/',
    #'Upgrade-Insecure-Requests': '1',
    #'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36',
}

# 2. 调用get函数
html_bytes = get(url, headers=headers)
# 3. 保存页面
with open('renren.html', 'wb') as f:
    f.write(html_bytes)