python 爬虫学习

Posted 2021-02-20 阿里云的奥斯卡

response = requests.get("http://www.baidu.com")

 response.content.decode("utf-8")  返回bytes类型 decode解码

 response.text    request.encoding = "gbk" # 修改编码 返回str类型 

 获取图片

# coding=utf-8
import requests
url = "http://wap.jiapai.net.cn/images/1.jpg"

response = requests.get(url)
with open("baidu.png","wb") as f:
    f.write(response.content)
                             

---

# 状态码 

response.status_code 

# 响应头

response.headers

# 请求头

response.request.headers

200
{‘Content-Length‘: ‘20851‘, ‘Content-Type‘: ‘image/jpeg‘, ‘Last-Modified‘: ‘Sun, 28 Jul 2019 04:29:48 GMT‘, ‘Accept-Ranges‘: ‘bytes‘, ‘ETag‘: ‘"1f3f6d17fd44d51:0"‘, ‘Set-Cookie‘: ‘sdwaf-test-item=1ed57f5405075208510954035156575b5c5754065406040d015701515e520c; path=/; HttpOnly‘, ‘X-Powered-By‘: ‘SDWAF‘, ‘Date‘: ‘Tue, 05 May 2020 01:56:48 GMT‘}
{‘User-Agent‘: ‘python-requests/2.23.0‘, ‘Accept-Encoding‘: ‘gzip, deflate‘, ‘Accept‘: ‘*/*‘, ‘Connection‘: ‘keep-alive‘}

 

---

# 发送带header的请求 

# coding=utf-8
import requests
url = "http://wap.jiapai.net.cn/images/1.jpg"
headers = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.129 Safari/537.36"}

response = requests.get(url,headers=headers)
print(response.status_code)
print(response.headers)
print(response.request.headers)

---

# 占位符 建议使用format+ {} 代替 

input_string = input("")

url = "http://www.baidu.com/s?wd={}".format(input_string) || url = "https://www.baidu.com/s?wd=%s"%input_string 

---