爬虫day 04_01(爬百度页面)

Posted 2020-10-14 窃语

import urllib.request
import http.cookiejar
from lxml import etree
head = {
    ‘Connection‘: ‘Keep-Alive‘,
    ‘Accept‘: ‘text/html, application/xhtml+xml, */*‘,
    ‘Accept-Language‘: ‘en-US,en;q=0.8,zh-Hans-CN;q=0.5,zh-Hans;q=0.3‘,
    ‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 6.3; WOW64; Trident/7.0; rv:11.0) like Gecko‘
}
# 给opener加上cookie
def makeMyOpener(head):
    cj = http.cookiejar.CookieJar()
    opener = urllib.request.build_opener(urllib.request.HTTPCookieProcessor(cj))
    header = []
    for key, value in head.items():
        elem = (key, value)
        header.append(elem)
    opener.addheaders = header
    return opener
# 通过cookie 爬百度
oper=makeMyOpener(head)
url="https://www.baidu.com/s?ie=utf-8&f=3&rsv_bp=1&rsv_idx=1&tn=baidu&wd=python%20str%20%E8%BD%AC%20int&oq=python%2520str%2520%25E8%25BD%25AC%2520int&rsv_pq=c24aa0760000154b&rsv_t=c323uk7fLXupzfPqhHcqM%2F6l8k7Re4K90ZvzI33LDwW0kHYMiSED9rhKzCg&rqlang=cn&rsv_enter=0&prefixsug=python%2520str%2520%25E8%25BD%25AC%2520int&rsp=0"
uop=oper.open(url,timeout=1000)
data=uop.read()
html=data.decode();
print(html)