各种例子（1）

#爬取百度页面
import urllib.request
import urllib.parse
key = input(‘请出入搜索的关键字:’)
url = ‘http://www.baidu.com/s?&’
data = {‘wd’:key,“ie”:“utf-8”}
data=urllib.parse.urlencode(data)
link = url+data
xiangying = urllib.request.urlopen(link).read()
filename = ‘C:/Users/mozat/Desktop/’+key+’.html’
with open(filename,‘wb’) as ft:
  ft.write(xiangying)

#get列子
import urllib.request
import urllib.parse
url = ‘https://movie.douban.com/j/chart/top_list?type=5&interval_id=100%3A90&action=&’
data = {“start”:20,“limit”:20}
head = {‘User-Agent’: ‘Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:71.0) Gecko/20100101 Firefox/71.0’}
data = urllib.parse.urlencode(data).encode()
duixiang = urllib.request.Request(url=url,headers=head)
xiangying = urllib.request.urlopen(duixiang,data=data)
print(xiangying.read().decode())

#爬取贴吧
import urllib.request
import urllib.parse
start = int(input(‘输入要爬取的起始页码:’))
end = int(input(‘输入要爬取的结束页码:’))
key = input(‘输入要爬取的关键字:’)
url = ‘http://tieba.baidu.com/f?’
head = {‘User-Agent’: ‘Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:71.0) Gecko/20100101 Firefox/71.0’}
for i in range(start,end+1):
  data = {“kw”:key,
      “ie”:‘utf-8’,
      “pn”:(i-1)*50,}
  data = urllib.parse.urlencode(data).encode()
  duixiang = urllib.request.Request(url=url,headers=head)
  xiangying = urllib.request.urlopen(duixiang,data=data)
  filename = ‘E:/test/’+str(i)+’.html’
  with open(filename,‘wb’) as ft:
   ft.write(xiangying.read())