get 百度

注意：百度搜索，headers中必须包含Cookie，否则是“百度安全验证”。

需求一：使用urllib实现百度搜索结果页面保存

import urllib.request
import urllib.parse
# https://www.baidu.com/s?wd=%E4%B8%96%E5%8D%9A%E5%9B%AD
BT = input('请输入你要搜索的内容:')
wd = {'wd':BT}
name = urllib.parse.urlencode(wd)
baseurl = 'https://www.baidu.com/s?'
url = baseurl + name
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.88 Safari/537.36','Cookie':'BIDUPSID=4FA733ACE6D4F90A52D99F5F363CD85A; PSTM=1576929032; sug=3; sugstore=0; ORIGIN=0; bdime=0; BAIDUID=4FA733ACE6D4F90A83BE743C46630339:SL=0:NR=10:FG=1; BD_UPN=12314753; BDUSS=VFPUlFGU0RER1ZtcDdTR1lPek5vcEdZcUMtRFNNUkN3VHZTb35Cb1hRR0duOHRlRVFBQUFBJCQAAAAAAAAAAAEAAADzvSajSjdnaGgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAIYSpF6GEqReR; MCITY=-158%3A; BDORZ=B490B5EBF6F3CD402E515D22BCDA1598; H_PS_PSSID=; H_PS_645EC=9e896%2FhdaWy7uBsYfIeQKxjhCoWB1I56kSiZk45G7DyeSZsVpqa6Fx3Np2k; COOKIE_SESSION=3052_0_9_9_86_16_0_0_9_8_15_0_0_0_10_0_1588076550_0_1588079592%7C9%235669_143_1586614174%7C9'}
req = urllib.request.Request(url,headers=headers)
res = urllib.request.urlopen(req)
html = res.read().decode('utf-8')
with open(BT + '.html','w',encoding='utf-8') as f:
    f.write(html)

需求二：使用requests实现百度搜索结果页面保存

import requests

BT = input('请输入你要搜索的内容:')
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.88 Safari/537.36','Cookie':'BIDUPSID=4FA733ACE6D4F90A52D99F5F363CD85A; PSTM=1576929032; sug=3; sugstore=0; ORIGIN=0; bdime=0; BAIDUID=4FA733ACE6D4F90A83BE743C46630339:SL=0:NR=10:FG=1; BD_UPN=12314753; BDUSS=VFPUlFGU0RER1ZtcDdTR1lPek5vcEdZcUMtRFNNUkN3VHZTb35Cb1hRR0duOHRlRVFBQUFBJCQAAAAAAAAAAAEAAADzvSajSjdnaGgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAIYSpF6GEqReR; MCITY=-158%3A; BDORZ=B490B5EBF6F3CD402E515D22BCDA1598; H_PS_PSSID=; H_PS_645EC=9e896%2FhdaWy7uBsYfIeQKxjhCoWB1I56kSiZk45G7DyeSZsVpqa6Fx3Np2k; COOKIE_SESSION=3052_0_9_9_86_16_0_0_9_8_15_0_0_0_10_0_1588076550_0_1588079592%7C9%235669_143_1586614174%7C9'}
wd = {'wd':BT}
url = 'https://www.baidu.com/s?'
response =requests.get(url,params=wd,headers=headers)
html = response.content.decode('utf-8')
with open(BT + '.html','w',encoding='utf-8') as f:
    f.write(html)

可以看出，requests不用手动解码关键字；不用实例化一个请求对象。