Project-2: 用python抓取包含关键词的网页

# #导入包
# import urllib
# import urllib.request
#
# wd = input('输入要搜索的关键字:')
# data = {}
# data['wd'] = wd
# #转换数据
# url_value = urllib.parse.urlencode(data)
# print(url_value)
# url = 'https://www.baidu.com/s?'
# full_url = url+url_value
# print(full_url)
# #发送请求，获取响应
# response = urllib.request.urlopen(full_url)
# #获取响应的内容
# data = response.read()
# #解码
# data = data.decode('utf-8')
# #打印
# print(data)



# 导入包
import urllib
import urllib.request

wd = input('输入要搜索的关键字:')
data = {}
data['wd'] = wd
#转换数据
url_value = urllib.parse.urlencode(data)
print(url_value)
url = 'https://www.baidu.com/s?'
full_url = url+url_value
print(full_url)
#请求头
headers={
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.139 Safari/537.36'
}
#准备请求对象，有参数：url,请求头
request = urllib.request.Request(url=full_url,headers=headers)
#发送请求，获取响应
response = urllib.request.urlopen(request)
#获取响应的内容
data = response.read()
#解码
# data = data.decode('utf-8')
#打印
# print(data)
#存储
with open('zhonghua.html','wb') as file:
    file.write(data)
print('结束...')

results: