Python Requests
跳转到导航
跳转到搜索
ins and usage
sudo apt install python3-pip
sudo pip3 install requests
>>> import requests
>>> dir(requests)
['ConnectTimeout', 'ConnectionError', 'DependencyWarning', 'FileModeWarning', 'HTTPError', 'JSONDecodeError', 'NullHandler', 'PreparedRequest', 'ReadTimeout', 'Request', 'RequestException', 'RequestsDependencyWarning', 'Response', 'Session', 'Timeout', 'TooManyRedirects', 'URLRequired', '__author__', '__author_email__', '__build__', '__builtins__', '__cached__', '__cake__', '__copyright__', '__description__', '__doc__', '__file__', '__license__', '__loader__', '__name__', '__package__', '__path__', '__spec__', '__title__', '__url__', '__version__', '_check_cryptography', '_internal_utils', 'adapters', 'api', 'auth', 'certs', 'chardet_version', 'charset_normalizer_version', 'check_compatibility', 'codes', 'compat', 'cookies', 'delete', 'exceptions', 'get', 'head', 'hooks', 'logging', 'models', 'options', 'packages', 'patch', 'post', 'put', 'request', 'session', 'sessions', 'ssl', 'status_codes', 'structures', 'urllib3', 'utils', 'warnings']
>>>
>>> r = requests.get("http://google.com")
>>> r.cookies
<RequestsCookieJar[Cookie(version=0, name='AEC', value='AVYB7cqAFnkbEnNvpWvGBA9ve1M_JSdKgo7mLU4GK1p1KZigxhf-Bipu2g', port=None, port_specified=False, domain='.google.com', domain_specified=True, domain_initial_dot=True, path='/', path_specified=True, secure=True, expires=1745391827, discard=False, comment=None, comment_url=None, rest={'HttpOnly': None, 'SameSite': 'lax'}, rfc2109=False), Cookie(version=0, name='NID', value='518=Ba-UW487XfcHFf6eSMcF1lioSHTcC3Zt2kzulMnC207wDs17OrwbxveIppcZ4u_B4Tcm9ZLO9IQguWhIzH_-zRU9GMPhf66LsSatS4dLTIP8CfexMbf0oJh3T2phHKsdZjyqIocWHNcKoyLqwuWO_YAmQYIDvI_jGx7zaoB31LKU2UjAU4EJpk-Bhht3vo3pVlpL', port=None, port_specified=False, domain='.google.com', domain_specified=True, domain_initial_dot=True, path='/', path_specified=True, secure=False, expires=1745651027, discard=False, comment=None, comment_url=None, rest={'HttpOnly': None}, rfc2109=False)]>
>>> r.cookies
<RequestsCookieJar[Cookie(version=0, name='AEC', value='AVYB7cqAFnkbEnNvpWvGBA9ve1M_JSdKgo7mLU4GK1p1KZigxhf-Bipu2g', port=None, port_specified=False, domain='.google.com', domain_specified=True, domain_initial_dot=True, path='/', path_specified=True, secure=True, expires=1745391827, discard=False, comment=None, comment_url=None, rest={'HttpOnly': None, 'SameSite': 'lax'}, rfc2109=False), Cookie(version=0, name='NID', value='518=Ba-UW487XfcHFf6eSMcF1lioSHTcC3Zt2kzulMnC207wDs17OrwbxveIppcZ4u_B4Tcm9ZLO9IQguWhIzH_-zRU9GMPhf66LsSatS4dLTIP8CfexMbf0oJh3T2phHKsdZjyqIocWHNcKoyLqwuWO_YAmQYIDvI_jGx7zaoB31LKU2UjAU4EJpk-Bhht3vo3pVlpL', port=None, port_specified=False, domain='.google.com', domain_specified=True, domain_initial_dot=True, path='/', path_specified=True, secure=False, expires=1745651027, discard=False, comment=None, comment_url=None, rest={'HttpOnly': None}, rfc2109=False)]>
>>> r.headers
{'Date': 'Fri, 25 Oct 2024 07:03:47 GMT', 'Expires': '-1', 'Cache-Control': 'private, max-age=0', 'Content-Type': 'text/html; charset=ISO-8859-1', 'Content-Security-Policy-Report-Only': "object-src 'none';base-uri 'self';script-src 'nonce-GYqphV2LY_t_XuymXSKByw' 'strict-dynamic' 'report-sample' 'unsafe-eval' 'unsafe-inline' https: http:;report-uri https://csp.withgoogle.com/csp/gws/other-hp", 'P3P': 'CP="This is not a P3P policy! See g.co/p3phelp for more info."', 'Content-Encoding': 'gzip', 'Server': 'gws', 'Content-Length': '9134', 'X-XSS-Protection': '0', 'X-Frame-Options': 'SAMEORIGIN', 'Set-Cookie': 'AEC=AVYB7cqAFnkbEnNvpWvGBA9ve1M_JSdKgo7mLU4GK1p1KZigxhf-Bipu2g; expires=Wed, 23-Apr-2025 07:03:47 GMT; path=/; domain=.google.com; Secure; HttpOnly; SameSite=lax, NID=518=Ba-UW487XfcHFf6eSMcF1lioSHTcC3Zt2kzulMnC207wDs17OrwbxveIppcZ4u_B4Tcm9ZLO9IQguWhIzH_-zRU9GMPhf66LsSatS4dLTIP8CfexMbf0oJh3T2phHKsdZjyqIocWHNcKoyLqwuWO_YAmQYIDvI_jGx7zaoB31LKU2UjAU4EJpk-Bhht3vo3pVlpL; expires=Sat, 26-Apr-2025 07:03:47 GMT; path=/; domain=.google.com; HttpOnly'}
>>> r.encoding
'ISO-8859-1'
>>> r.status_code
200
>>>
响应格式
content 返回是的二进制的内容，text返回是字符串格式的内容，json()返回的是序列化的内容。
post
构造url
我们常常将http请求的参数以url的query string的形式进行发送，传统的做法是我们使用拼凑的方式构造这个url。例如我们需要构造以下这个url：
http://httpbin.org/get?key1=value1&key2=value2
使用reqeuets，你可以方便地构造这个url，而不用手工拼凑。你只需要将这些参数和值构造一个字典，然后将这个字典传给params参数即可
传递一个字典给data参数
>>> import requests
>>> payload={"key1":"value1","key2":"value2"}
>>> r=requests.post("https://httpbin.org/post")
>>> r1=requests.post("https://httpbin.org/post",data=payload)
>>>
有没有参考的不同
>>> r.text
'{\n "args": {}, \n "data": "", \n "files": {}, \n "form": {}, \n "headers": {\n "Accept": "*/*", \n "Accept-Encoding": "gzip, deflate, br", \n "Content-Length": "0", \n "Host": "httpbin.org", \n "User-Agent": "python-requests/2.28.1", \n "X-Amzn-Trace-Id": "Root=1-671b4668-1f54cdbc43c5b947731a92b5"\n }, \n "json": null, \n "origin": "146.190.165.134", \n "url": "https://httpbin.org/post"\n}\n'
>>> r1.text
'{\n "args": {}, \n "data": "", \n "files": {}, \n "form": {\n "key1": "value1", \n "key2": "value2"\n }, \n "headers": {\n "Accept": "*/*", \n "Accept-Encoding": "gzip, deflate, br", \n "Content-Length": "23", \n "Content-Type": "application/x-www-form-urlencoded", \n "Host": "httpbin.org", \n "User-Agent": "python-requests/2.28.1", \n "X-Amzn-Trace-Id": "Root=1-671b46b8-2b9d0e294d20bcc104da3fb3"\n }, \n "json": null, \n "origin": "146.190.165.134", \n "url": "https://httpbin.org/post"\n}\n'
>>>
http header
>>> r.headers['content-type'] 'application/json' >>> r.headers['content-type']='ada' >>> r.headers['content-type'] 'ada'
get
In [20]: url3 ='https://www.weather.com.cn/data/sk/10113010.html'
In [21]: r3 = requests.get(url3)
In [32]: ku_url='https://www.kuaidi100.com/query'
In [33]: params = {'type': 'youzhengguonei','postid': '9893442769997'}
In [35]: r = requests.get(ku_url,params=params)
In [36]: r.json()
Out[36]:
{'message': 'ok',
'nu': '9893442769997',
'ischeck': '1',
'com': 'youzhengguonei',
'status': '200',
'condition': 'F00',
'state': '3',
'data': [{'time': '2024-11-05 11:44:13',
'context': '查无结果',
'ftime': '2024-11-05 11:44:13'}]}
#加头
In [37]: js_url = 'http://www.jianshu.com'
In [38]: r=requests.get(js_url)
In [39]: r.text
Out[39]: '<html>\r\n<head><title>403 Forbidden</title></head>\r\n<body>\r\n<center><h1>403 Forbidden</h1></center>\r\n<hr><center>openresty</center>\r\n</body>\r\n</html>\r\n'
In [40]: headers = {'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:133.0) Gecko/20100101 Firefox/133.0'}
In [41]: r=requests.get(js_url,headers=headers)
#出东西
r.text
img
url2 = 'https://img02.sogoucdn.com/app/a/100520021/46b805167ca269bbfc35922057a14665'
r2 = requests.get(url2)
In [18]: with open('/tmp/i.jpg','wb') as fobj:
...: fobj.write(r2.content)
requests模块-发送带参数的请求
1. url 中直接带参数 2. 使用params 参数
返回值类型
r.content：返回的是响应内容的二进制形式，类型为 bytes。这意味着它可以包含任何类型的数据，比如图片、音频、视频等二进制文件，也可以是文本数据。 r.text：返回的是响应内容的字符串形式，类型为 str。它会尝试根据响应的 Content-Type 头部信息或自动检测来对二进制数据进行解码。
2. 代码示例及区别展示
python
import requests
- 发送 HTTP 请求
r = requests.get('https://www.example.com')
- 使用 r.content 获取二进制响应内容
content = r.content print(type(content)) # 输出: <class 'bytes'>
- 使用 r.text 获取字符串响应内容
text = r.text print(type(text)) # 输出: <class 'str'>
eg 之钉钉机器发群消息
import requests
import json
import getpass
#前提先创建群
# url =getpass.getpass() #要手工输入
url= 'https://oapi.dingtalk.com/robot/send?access_token=97a2b9rrrrrdc9632931119269cf4rrrrr8ff4ff1890e471805faf586'
headers = {'Content-Type': 'application/json;charset=utf-8'}
data ={
"msgtype": "text",
"text": {
"content": "我就是我 好好学习天天向上 @18520124378"
},
"at": {
"atMobiles": [
"18520124378"
],
"isAtAll": False, # 不@所有人
}
}
r = requests.post(url,headers=headers,data=json.dumps(data))
print(r.json())
# (master) ✗ python dingtalk.py
# Password:
# {'errcode': 310000, 'errmsg': '错误描述:关键词不匹配;解决方案:请联系群管理员查看此机器人的关键词，并在发送的信息中包含此关键词;'}
# ➜ drf_tutorial git:(master) ✗ python dingtalk.py
# {'errcode': 0, 'errmsg': 'ok'}
eg 2
#!/usr/bin/env python3
import json
import requests
import sys
def send_msg(url, reminders, msg):
headers = {'Content-Type': 'application/json;charset=utf-8'}
data = {
"msgtype": "text", # 发送消息类型为文本
"at": {
"atMobiles": reminders,
"isAtAll": False, # 不@所有人
},
"text": {
"content": msg, # 消息正文
}
}
r = requests.post(url, data=json.dumps(data), headers=headers)
return r.text
if __name__ == '__main__':
msg = sys.argv[1]
reminders = ['15055667788'] # 特殊提醒要查看的人,就是@某人一下
url = 此处填写上面第5步webhook的内容
print(send_msg(url, reminders, msg))
# python3 dingtalk.py "这是一个测试而已"
https://open.dingtalk.com/document/robots/customize-robot-security-settings
Python获取天气并email通知
king
v1
import requests
# 获取翻译包的url
url = 'https://ifanyi.iciba.com/index.php?c=trans'
# 构建请求头
headers = {
'User-Agent': '', # 每个人的User_Agent不同，自己可以通过抓的包里复制粘贴
'Referer': 'https://www.iciba.com/',
'Host': 'ifanyi.iciba.com'
}
# 实现用户输入的功能
content = input('请输入您想翻译的内容：')
# 构建参数字典
post_data = {
'from': 'zh',
'to': 'en',
'q' : content,
}
# 发送请求
res = requests.post(url, headers=headers, data=post_data)
res_1 = res.content.decode()
print(eval(res_1)['out'])
v2
import requests
import json
# 获取翻译 API 的 URL
url = 'https://ifanyi.iciba.com/index.php?c=trans'
# 构建请求头，填充 User-Agent 避免被拦截
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36',
'Referer': 'https://www.iciba.com/',
'Host': 'ifanyi.iciba.com'
}
# 用户输入待翻译内容
content = input('请输入您想翻译的内容：').strip()
# 构建请求参数
post_data = {
'from': 'zh', # 源语言
'to': 'en', # 目标语言
'q': content,
}
try:
# 发送 POST 请求
res = requests.post(url, headers=headers, data=post_data, timeout=5)
res.raise_for_status() # 检查请求是否成功
# 解析 JSON 数据
res_json = res.json()
# 提取翻译结果
if 'out' in res_json:
print(f'翻译结果：{res_json["out"]}')
else:
print('翻译失败，API 响应格式错误！')
except requests.exceptions.RequestException as e:
print(f'请求错误：{e}')
except json.JSONDecodeError:
print('解析 JSON 失败，返回的数据格式有误！')
v3 OOP
import requests
import json
class Translator:
def __init__(self, word):
self.url = 'https://ifanyi.iciba.com/index.php?c=trans'
self.headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36',
'Referer': 'https://www.iciba.com/',
'Host': 'ifanyi.iciba.com'
}
self.data = {
'from': 'zh',
'to': 'en',
'q': word # 动态传入用户输入的文本
}
def get_postdata(self):
""" 发送 POST 请求获取翻译结果 """
try:
response = requests.post(self.url, data=self.data, headers=self.headers, timeout=5)
response.raise_for_status() # 检查 HTTP 状态码
return response.content # 返回原始 JSON 响应
except requests.exceptions.RequestException as e:
print(f"请求失败：{e}")
return None
def parse_data(self, data):
""" 解析 JSON 数据并提取翻译内容 """
if not data:
print("未收到有效数据，无法解析。")
return
try:
result = json.loads(data) # 解析 JSON
if 'out' in result:
print(f'翻译结果：{result["out"]}')
else:
print('翻译失败，API 响应格式可能已变更。')
except json.JSONDecodeError:
print('解析 JSON 失败，返回的数据格式有误！')
def run(self):
""" 执行翻译逻辑 """
response_data = self.get_postdata()
self.parse_data(response_data)
if __name__ == '__main__':
user_input = input('请输入您想翻译的内容：').strip()
translator = Translator(user_input)
translator.run()
流程其实如下
请输入您想翻译的内容：你好
↓
get_postdata() 发送请求
↓
API 返回 JSON（字节流）
↓
run() 接收数据，并调用 parse_data()
↓
parse_data() 解析 JSON，提取 `out`
↓
输出翻译结果：Hello
see also
Python进阶】Python网络游侠：揭开requests库的神秘面纱
详解python使用金山词霸的翻译功能(调试工具断点的使用)
https://www.runoob.com/python3/python-requests.html
官方 quickstart 算看了 https://requests.readthedocs.io/en/latest/user/quickstart/
视频
requests零基础 Python3的requests库使用教程，让你从入门到精通
【requests零基础】Python3的requests库使用教程，让你从入门到精通
意外
自己随便起名的坑 哈哈 不要和系统的东西同名
information.
>>> import requests
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/home/evan/.local/lib/python3.11/site-packages/requests/__init__.py", line 43, in <module>
import urllib3
File "/usr/lib/python3/dist-packages/urllib3/__init__.py", line 13, in <module>
from .connectionpool import HTTPConnectionPool, HTTPSConnectionPool, connection_from_url
File "/usr/lib/python3/dist-packages/urllib3/connectionpool.py", line 37, in <module>
from six.moves import queue
File "<frozen importlib._bootstrap>", line 1229, in _handle_fromlist
File "/usr/lib/python3/dist-packages/six.py", line 97, in __get__
result = self._resolve()
^^^^^^^^^^^^^^^
File "/usr/lib/python3/dist-packages/six.py", line 120, in _resolve
return _import_module(self.mod)
^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/lib/python3/dist-packages/six.py", line 87, in _import_module
__import__(name)
File "/home/evan/data/python/tmp/queue.py", line 26
# pr.terminate()
^
IndentationError: expected an indented block after 'if' statement on line 18
代码在导入 requests 库时出错，最终错误指向你本地的 queue.py 文件里存在 IndentationError，也就是缩进错误
well done
➜ tmp mv queue.py queue.pybak
➜ tmp python
Python 3.12.6 (main, Sep 7 2024, 14:20:15) [GCC 14.2.0] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> import requests
>>>