python爬虫基础知识
文章目录
1. 请求
# 基本用法
import requests
response = requests.get('http://httpbin.org/get')
print(response.text)
1.1. 带参数的get请求
# 带参数的get请求
import requests
response = requests.get('http://httpbin.org/get?name=germey&age=22')
print(response.text)
import requests
data = {
'name': 'germey',
'age':22
}
response = requests.get('http://httpbin.org/get', params=data)
print(response.text)
1.2. 解析json
import requests
response = requests.get('http://httpbin.org/get')
print(type(response.text)) # str
print(response.json())
print(type(response.json())) #dict
1.3. 获取二进制数据
# 获取二进制数据,比如图片
import requests
response = requests.get("http://github.com/favicon.ico")
print(type(response.text), type(response.content))
print(response.text)
print(response.content)
将获取的二进制文件(这里是一张图片)保存下来.
import requests
response = requests.get("http://github.com/favicon.ico")
with open('favicon.ico', 'wb') as f:
f.write(response.content)
f.close()
1.4. 增加请求头信息
获取不到有用信息
# 增加请求头
import requests
response = requests.get("https://www.zhihu.com/explore")
print(response.text)
增加请求头之后才可以获取需要的信息
# 增加请求头
import requests
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:72.0) Gecko/20100101 Firefox/72.0'
}
response = requests.get("https://www.zhihu.com/explore", headers=headers)
print(response.text)
1.5. post请求
# post请求
import requests
data = {'name':'germey', 'age':20}
response = requests.post('http://httpbin.org/post', data=data)
print(response.text)
增加headers
# post请求
import requests
data = {'name':'germey', 'age':20}
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:72.0) Gecko/20100101 Firefox/72.0'
}
response = requests.post('http://httpbin.org/post', data=data, headers=headers)
print(response.json())
2. 响应
import requests
response = requests.get('http://www.jianshu.com')
print(type(response.status_code), response.status_code)
print(type(response.headers), response.headers)
print(type(response.cookies), response.cookies)
print(type(response.url), response.url)
print(type(response.history), response.history)
2.1. 状态码判断
# 状态码使用
import requests
response = requests.get('http://www.jianshu.com')
print("request failed") if not response.status_code == requests.codes.ok else print("request successfully")
另一种方式
# 状态码使用
import requests
response = requests.get('http://www.jianshu.com')
print("request failed") if not response.status_code == 200 else print("request successfully")
here整理的有每个状态码对应的解释说明。
3. 高级操作
3.1. 文件上传
import requests
# 这里的file是自己命名的,在服务器就可以根据这个file拿到上传的文件。
files = {'file': open('favicon.ico', 'rb')}
response = requests.post('http://httpbin.org/post', files=files)
print(response.text)
3.2. 获取cookie
# 获取cookie
import requests
response = requests.get("http://www.baidu.com")
print(response.cookies)
for key, value in response.cookies.items():
print(key+"="+value)
3.3. 会话维持
参考here