【Python】python 爬虫学习

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)

---

# 发送带参数的请求 

params = {"":""}

url_temp = "www.baidu.com/s?"

requests.get(url_temp,params=params)

---

# 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 

---

列表推导式

# 范围0~9 

[i for i in range(10)]

# i对2取余 输出 

[i%2 for i in range(10)]

# i对2取余，如果对而取余等于0 则输出 

[i%2 for i in range(10) if i%2==0]

---

## 面向对象 

- 对象

  - 生活中的事务

- 类

  - 对事务的抽象 在代码中实现class 类型

- 实例

  - 使用之前对类的实例化之后的结果

--- 

# get 请求贴吧 

# coding=utf-8
import requests

class TiebaSpider:
    def __init__(self,tieba_name):
        self.tieba_name = tieba_name
        self.url_temp = "https://tieba.baidu.com/f?kw="+tieba_name+"&ie=utf-8&pn={}"
        self.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"}

    def get_url_list(self):
        return [self.url_temp.format(i*50) for i in range(10)]

    def parse_url(self, url):
        response = requests.get(url, headers=self.headers)
        return response.content.decode("utf-8")

    def save_html_str(self, html_str, page_num):
        file_path = "{}-第{}页".format(self.tieba_name, page_num)
        with open(file_path, "w", encoding="utf-8") as f:
            f.write(html_str)

    def run(self):
        # 1 构造url 
        url_list = self.get_url_list()

        # 2 发送请求 获取相应 
for url in url_list:
            html_str = self.parse_url(url)

        # 3 保存 
            page_num = url_list.index(url) + 1
            self.save_html_str(html_str, page_num)

if __name__ == "__main__":
    tieba_spider = TiebaSpider("李毅")
    tieba_spider.run()
                                      

# 保存贴吧内容到本地 

---

# Post 请求  安全 大文本传输 

data = {"":""}  # 字典

requests.post("https://www.baidu.com",data = data,headers=headers)