关于python爬虫应用urllib库作用分析

# -*- codeing = utf-8 -*-
# @Author: Y-peak
# @Time : 2021/9/2 19:24
# @FileName : testUrllib.py
# Software : PyCharm
import urllib.request
#get请求
response = urllib.request.urlopen("http://www.baidu.com")  #返回的是存储网页数据的对象
#print(response)  可以尝试打印一下看一下
print(response.read().decode('utf-8')) #通过read将数据读取出来, 使用utf-8解码防止有的地方出现乱码

# -*- codeing = utf-8 -*-
# @Author: Y-peak
# @Time : 2021/9/2 19:24
# @FileName : testUrllib.py
# Software : PyCharm
import urllib.request
response = urllib.request.urlopen("http://www.baidu.com")  #返回的是存储网页数据的对象
data = response.read().decode('utf-8')  #通过read将数据读取出来, 使用utf-8解码防止有的地方出现乱码
#print(data)
with open("index.html",'w',encoding='utf-8') as wfile: #或者你们也可以常规打开，不过需要最后关闭记得close()
    wfile.write(data)
    print("读取结束")

# -*- codeing = utf-8 -*-
# @Author: Y-peak
# @Time : 2021/9/2 19:24
# @FileName : testUrllib.py
# Software : PyCharm
import urllib.request
import urllib.parse #解析器
data = bytes(urllib.parse.urlencode({"hello":"world"}),encoding='utf-8')  #转换为二进制数据包，里面是键值对（有时输入的用户名：密码就是这样的），还有一些编码解码的数值等.这里就是按照utf-8的格式进行解析封装生成二进制数据包
response = urllib.request.urlopen("http://httpbin.org/post",data=data)  #返回的请求
print(response.read().decode('utf-8'))      #通过read将数据读取出来, 使用utf-8解码防止有的地方出现乱码

# -*- codeing = utf-8 -*-
# @Author: Y-peak
# @Time : 2021/9/2 19:24
# @FileName : testUrllib.py
# Software : PyCharm
import urllib.request
try:
    response = urllib.request.urlopen("http://httpbin.org/get",timeout=0.01)  #返回的是存储网页数据的对象, 直接用这个网址的get请求了.timeout表示超时，超过0.01秒不响应就报错，避免持续等待
    print(response.read().decode('utf-8'))      #通过read将数据读取出来, 使用utf-8解码防止有的地方出现乱码
except urllib.error.URLError as e:
    print("超时了\t\t错误为：",e)

# -*- codeing = utf-8 -*-
# @Author: Y-peak
# @Time : 2021/9/2 19:24
# @FileName : testUrllib.py
# Software : PyCharm
import urllib.request
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.159 Safari/537.36"
}
request = urllib.request.Request("http://douban.com", headers=headers) #返回的是请求，将我们伪装成浏览器发送的请求
response = urllib.request.urlopen(request)  #返回的是存储网页数据的对象
data = response.read().decode('utf-8')     #通过read将数据读取出来, 使用utf-8解码防止有的地方出现乱码
with open("index.html",'w',encoding='utf-8') as wfile: #或者你们也可以常规打开，不过需要最后关闭记得close()
    wfile.write(data)

# -*- codeing = utf-8 -*-
# @Author: Y-peak
# @Time : 2021/9/3 0:47
# @FileName : testUrllib.py
# Software : PyCharm

import urllib.request
import urllib.parse
headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.159 Safari/537.36"
}
url = "http://httpbin.org/post"
data = (bytes)(urllib.parse.urlencode({"账户":"密码"}),encoding = 'utf-8')
request = urllib.request.Request(url, data = data,headers=headers, method='POST') #返回的是请求
response = urllib.request.urlopen(request)  #返回的是存储网页数据的对象
data = response.read().decode('utf-8')     #通过read将数据读取出来, 使用utf-8解码防止有的地方出现乱码
print(data)