update python_requests.py
parent
6179eada84
commit
d7e070307a
|
@ -6,48 +6,59 @@ python_requests.py by xianhu
|
||||||
|
|
||||||
import requests
|
import requests
|
||||||
|
|
||||||
# 尝试获取某个网页, 这里的r是一个Response对象
|
# 不同方式获取网页内容, 返回一个Response对象, 请求的参数可以为url或Request对象
|
||||||
r = requests.get("https://github.com/timeline.json")
|
r0 = requests.get("https://github.com/timeline.json")
|
||||||
print(type(r))
|
|
||||||
|
|
||||||
# Requests简便的API意味着所有HTTP请求类型都是显而易见的
|
|
||||||
r1 = requests.post("http://httpbin.org/post")
|
r1 = requests.post("http://httpbin.org/post")
|
||||||
r2 = requests.put("http://httpbin.org/put")
|
r2 = requests.put("http://httpbin.org/put")
|
||||||
r3 = requests.delete("http://httpbin.org/delete")
|
r3 = requests.delete("http://httpbin.org/delete")
|
||||||
r4 = requests.head("http://httpbin.org/get")
|
r4 = requests.head("http://httpbin.org/get")
|
||||||
r5 = requests.options("http://httpbin.org/get")
|
r5 = requests.options("http://httpbin.org/get")
|
||||||
|
r6 = requests.patch("http://httpbin.org/get")
|
||||||
|
|
||||||
# 传递URL参数: 字典
|
# Request对象:
|
||||||
payload = {"key1": "value1", "key2": "value2"}
|
# class requests.Request(method=None, url=None, headers=None, files=None, data=None, params=None, auth=None, cookies=None, hooks=None, json=None)
|
||||||
r = requests.get("http://httpbin.org/get", params=payload)
|
|
||||||
|
# 上边所有的获取方式都调用底层的request方法, 所以request方法有的参数, 上边几个函数都应该有:
|
||||||
|
# requests.request(method, url, **kwargs)
|
||||||
|
# kwargs包括: params / data / json / headers / cookies / files / auth / timeout / allow_redirects(bool) / proxies / verify(bool) / stream / cert
|
||||||
|
|
||||||
|
# Response对象: class requests.Response
|
||||||
|
# 包含的主要属性: content / cookies / encoding / headers / history / is_permanent_redirect / is_redirect / reason / status_code / text / url 等
|
||||||
|
# 包含的主要方法: iter_content(chunk_size=1, decode_unicode=False) / iter_lines(chunk_size=512, decode_unicode=None, delimiter=None)
|
||||||
|
# 包含的主要方法: close() / json(**kwargs) / raise_for_status() 等
|
||||||
|
|
||||||
|
# 以字典的形式传递URL参数, 也可以直接以?xx=xx&xx=xx的形式将其放在url后
|
||||||
|
params = {"key1": "value1", "key2": "value2"}
|
||||||
|
r = requests.get("http://httpbin.org/get", params=params)
|
||||||
print(r.url) # http://httpbin.org/get?key2=value2&key1=value1
|
print(r.url) # http://httpbin.org/get?key2=value2&key1=value1
|
||||||
|
|
||||||
# 传递URL参数: 字典里带有列表
|
# 以字典的形式传递URL参数: 字典里带有列表
|
||||||
payload = {"key1": "value1", "key2": ["value2", "value3"]}
|
params = {"key1": "value1", "key2": ["value2", "value3"]}
|
||||||
r = requests.get("http://httpbin.org/get", params=payload)
|
r = requests.get("http://httpbin.org/get", params=params)
|
||||||
print(r.url) # http://httpbin.org/get?key1=value1&key2=value2&key2=value3
|
print(r.url) # http://httpbin.org/get?key1=value1&key2=value2&key2=value3
|
||||||
|
|
||||||
# 获取正常内容
|
# 获取网页内容
|
||||||
r = requests.get("https://github.com/timeline.json")
|
r = requests.get("https://github.com/timeline.json")
|
||||||
print(r.text) # "[{"repository":{"open_issues":0,"url":"https://github.com/...
|
print(r.text) # 返回正常的网页内容, 即解压解码之后的内容
|
||||||
print(r.encoding) # "utf-8"
|
print(r.content) # 返回byte类型的网页内容, 即值解压, 没有解码
|
||||||
|
print(r.json()) # 如果网页内容为json, 直接返回一个json对象
|
||||||
|
print(r.encoding) # 返回网页的编码: "utf-8"
|
||||||
|
|
||||||
# Requests会自动解码来自服务器的内容(基于HTTP头部对响应的编码作出有根据的推测), 或者你自己更改
|
# Requests会自动解码来自服务器的内容, 也可以自己更改
|
||||||
r.encoding = "ISO-8859-1"
|
r.encoding = "ISO-8859-1"
|
||||||
print(r.text) # 此时使用新的r.encoding新值
|
print(r.text) # 此时使用新的r.encoding解码后的新值
|
||||||
|
|
||||||
# 二进制响应内容, Requests会自动为你解码 gzip 和 deflate 传输编码的响应数据
|
# 编码的其他操作
|
||||||
print(r.content) # b"[{"repository":{"open_issues":0,"url":"https://github.com/...
|
# requests.utils.get_encodings_from_content(content): Returns encodings from given content string.
|
||||||
|
# requests.utils.get_encoding_from_headers(headers): Returns encodings from given HTTP Header Dict.
|
||||||
# JSON 响应内容, Requests中也有一个内置的JSON解码器
|
# requests.utils.get_unicode_from_response(r): Returns the requested content back in unicode.
|
||||||
print(r.json()) # [{u"repository": {u"open_issues": 0, u"url": "https://github.com/...
|
|
||||||
|
|
||||||
# 原始响应内容: 获取来自服务器的原始套接字响应
|
# 原始响应内容: 获取来自服务器的原始套接字响应
|
||||||
r = requests.get("https://github.com/timeline.json", stream=True)
|
r = requests.get("https://github.com/timeline.json", stream=True)
|
||||||
print(r.raw) # <requests.packages.urllib3.response.HTTPResponse object at 0x101194810>
|
print(r.raw) # <requests.packages.urllib3.response.HTTPResponse object at 0x101194810>
|
||||||
print(r.raw.read(10)) # "\x1f\x8b\x08\x00\x00\x00\x00\x00\x00\x03"
|
print(r.raw.read(10)) # "\x1f\x8b\x08\x00\x00\x00\x00\x00\x00\x03"
|
||||||
|
|
||||||
# 但一般情况下, 应该以下面的模式将文本流保存到文件
|
# 一般情况下, 应该以下面的模式将文本流保存到文件
|
||||||
with open("test", "wb") as fd:
|
with open("test", "wb") as fd:
|
||||||
for chunk in r.iter_content(chunk_size=256):
|
for chunk in r.iter_content(chunk_size=256):
|
||||||
fd.write(chunk)
|
fd.write(chunk)
|
||||||
|
@ -56,11 +67,23 @@ with open("test", "wb") as fd:
|
||||||
# 定制请求头: 一个字典
|
# 定制请求头: 一个字典
|
||||||
headers = {"user-agent": "my-app/0.0.1"}
|
headers = {"user-agent": "my-app/0.0.1"}
|
||||||
r = requests.get("https://api.github.com/some/endpoint", headers=headers)
|
r = requests.get("https://api.github.com/some/endpoint", headers=headers)
|
||||||
print(r.request.headers) # 获取该请求的头部
|
print(r.request.headers) # 获取request的头部
|
||||||
|
print(r.headers) # 获取response的头部
|
||||||
|
# {
|
||||||
|
# "content-encoding": "gzip",
|
||||||
|
# "transfer-encoding": "chunked",
|
||||||
|
# "connection": "close",
|
||||||
|
# "server": "nginx/1.0.4",
|
||||||
|
# "x-runtime": "148ms",
|
||||||
|
# "etag": "e1ca502697e5c9317743dc078f67693f",
|
||||||
|
# "content-type": "application/json"
|
||||||
|
# }
|
||||||
|
print(r.headers["Content-Type"]) # "application/json"
|
||||||
|
print(r.headers.get("content-type")) # "application/json"
|
||||||
|
|
||||||
# 更加复杂的POST请求: 表单
|
# 更加复杂的POST请求: 表单
|
||||||
payload = {"key1": "value1", "key2": "value2"}
|
post_dict = {"key1": "value1", "key2": "value2"}
|
||||||
r = requests.post("http://httpbin.org/post", data=payload)
|
r = requests.post("http://httpbin.org/post", data=post_dict)
|
||||||
print(r.text)
|
print(r.text)
|
||||||
|
|
||||||
# POST一个多部分编码(Multipart-Encoded)的文件
|
# POST一个多部分编码(Multipart-Encoded)的文件
|
||||||
|
@ -73,7 +96,7 @@ files = {"file": ("report.xls", open("report.xls", "rb"), "application/vnd.ms-ex
|
||||||
r = requests.post("http://httpbin.org/post", files=files)
|
r = requests.post("http://httpbin.org/post", files=files)
|
||||||
print(r.text)
|
print(r.text)
|
||||||
|
|
||||||
# 你也可以发送作为文件来接收的字符串
|
# 你也可以发送文本字符串
|
||||||
files = {"file": ("report.csv", "some,data,to,send\nanother,row,to,send\n")}
|
files = {"file": ("report.csv", "some,data,to,send\nanother,row,to,send\n")}
|
||||||
r = requests.post("http://httpbin.org/post", files=files)
|
r = requests.post("http://httpbin.org/post", files=files)
|
||||||
print(r.text)
|
print(r.text)
|
||||||
|
@ -86,35 +109,25 @@ print(r.status_code == requests.codes.ok) # True 响应状态码查询
|
||||||
# 如果发送了一个错误请求(4XX客户端错误, 或5XX服务器错误响应), 可以通过 Response.raise_for_status() 来抛出异常:
|
# 如果发送了一个错误请求(4XX客户端错误, 或5XX服务器错误响应), 可以通过 Response.raise_for_status() 来抛出异常:
|
||||||
bad_r = requests.get("http://httpbin.org/status/404")
|
bad_r = requests.get("http://httpbin.org/status/404")
|
||||||
print(bad_r.status_code) # 404
|
print(bad_r.status_code) # 404
|
||||||
bad_r.raise_for_status()
|
bad_r.raise_for_status() # 引发异常
|
||||||
# Traceback (most recent call last):
|
|
||||||
# File "requests/models.py", line 832, in raise_for_status
|
|
||||||
# raise http_error
|
|
||||||
# requests.exceptions.HTTPError: 404 Client Error
|
|
||||||
|
|
||||||
# 响应头, 一个Python字典形式展示的服务器响应头, HTTP头部是大小写不敏感的
|
# Cookie: 如果某个响应中包含一些cookie, 则会被放到response.cookies(CookieJar类型)中
|
||||||
print(r.headers)
|
|
||||||
# {
|
|
||||||
# "content-encoding": "gzip",
|
|
||||||
# "transfer-encoding": "chunked",
|
|
||||||
# "connection": "close",
|
|
||||||
# "server": "nginx/1.0.4",
|
|
||||||
# "x-runtime": "148ms",
|
|
||||||
# "etag": "e1ca502697e5c9317743dc078f67693f",
|
|
||||||
# "content-type": "application/json"
|
|
||||||
# }
|
|
||||||
print(r.headers["Content-Type"]) # "application/json"
|
|
||||||
print(r.headers.get("content-type")) # "application/json"
|
|
||||||
|
|
||||||
# Cookie: 如果某个响应中包含一些 cookie
|
|
||||||
r = requests.get("http://example.com/some/cookie/setting/url")
|
r = requests.get("http://example.com/some/cookie/setting/url")
|
||||||
print(r.cookies["example_cookie_name"]) # "example_cookie_value"
|
print(r.cookies["example_cookie_name"]) # "example_cookie_value"
|
||||||
|
|
||||||
# 要想发送你的cookies到服务器, 可以使用cookies参数, 一个字典
|
# 要想发送你的cookies到服务器, 可以使用cookies参数(一个字典)
|
||||||
cookies = dict(cookies_are="working")
|
cookies = dict(cookies_are="working")
|
||||||
r = requests.get("http://httpbin.org/cookies", cookies=cookies)
|
r = requests.get("http://httpbin.org/cookies", cookies=cookies)
|
||||||
print(r.text)
|
print(r.text)
|
||||||
|
|
||||||
|
# cookie的其他操作
|
||||||
|
# requests.utils.dict_from_cookiejar(cj): Returns a key/value dictionary from a CookieJar.
|
||||||
|
# requests.utils.cookiejar_from_dict(cookie_dict, cookiejar=None, overwrite=True): Returns a CookieJar from a key/value dictionary.
|
||||||
|
# requests.utils.add_dict_to_cookiejar(cj, cookie_dict): Returns a CookieJar from a key/value dictionary.
|
||||||
|
|
||||||
|
# 通用CookieJar类, 一个cookielib.CookieJar, 但是提供一个dict接口
|
||||||
|
# class requests.cookies.RequestsCookieJar(policy=None): Compatibility class; is a cookielib.CookieJar, but exposes a dict interface.
|
||||||
|
|
||||||
# 会话对象: 会话对象让你能够跨请求保持某些参数, 它也会在同一个Session实例发出的所有请求之间保持cookie
|
# 会话对象: 会话对象让你能够跨请求保持某些参数, 它也会在同一个Session实例发出的所有请求之间保持cookie
|
||||||
s = requests.Session()
|
s = requests.Session()
|
||||||
s.get("http://httpbin.org/cookies/set/sessioncookie/123456789")
|
s.get("http://httpbin.org/cookies/set/sessioncookie/123456789")
|
||||||
|
@ -122,6 +135,9 @@ s.get("http://httpbin.org/cookies")
|
||||||
for cookie in s.cookies:
|
for cookie in s.cookies:
|
||||||
print(cookie)
|
print(cookie)
|
||||||
|
|
||||||
|
# 如果你要手动为会话添加cookie, 就是用Cookie utility函数来操纵Session.cookies
|
||||||
|
requests.utils.add_dict_to_cookiejar(s.cookies, {"cookie_key": "cookie_value"})
|
||||||
|
|
||||||
# 会话也可用来为请求方法提供缺省数据, 这是通过为会话对象的属性提供数据来实现的
|
# 会话也可用来为请求方法提供缺省数据, 这是通过为会话对象的属性提供数据来实现的
|
||||||
s.auth = ("user", "pass")
|
s.auth = ("user", "pass")
|
||||||
s.headers.update({"x-test": "true"})
|
s.headers.update({"x-test": "true"})
|
||||||
|
@ -131,30 +147,19 @@ s.get("http://httpbin.org/headers", headers={"x-test2": "true"}) # both "
|
||||||
s.get("http://httpbin.org/cookies", cookies={"from-my": "browser"}) # 带有cookie
|
s.get("http://httpbin.org/cookies", cookies={"from-my": "browser"}) # 带有cookie
|
||||||
s.get("http://httpbin.org/cookies") # 不带cookie
|
s.get("http://httpbin.org/cookies") # 不带cookie
|
||||||
|
|
||||||
# 如果你要手动为会话添加cookie, 就是用Cookie utility函数来操纵Session.cookies
|
|
||||||
requests.utils.add_dict_to_cookiejar(s.cookies, {"cookie_key": "cookie_value"})
|
|
||||||
for cookie in s.cookies:
|
|
||||||
print(cookie)
|
|
||||||
|
|
||||||
# 会话还可以用作前后文管理器
|
# 会话还可以用作前后文管理器
|
||||||
with requests.Session() as s:
|
with requests.Session() as s:
|
||||||
s.get("http://httpbin.org/cookies/set/sessioncookie/123456789")
|
s.get("http://httpbin.org/cookies/set/sessioncookie/123456789")
|
||||||
|
# class requests.Session类, 和requests外层有的函数/属性基本一致, 只不过是封装了一层跨域请求的功能
|
||||||
|
|
||||||
# 重定向与请求历史, 默认情况下, 除了HEAD, Requests会自动处理所有重定向
|
# 重定向与请求历史, 默认情况下, 除了HEAD, Requests会自动处理所有重定向, 可以通过allow_redirects参数禁用重定向处理
|
||||||
# 可以使用响应对象的history方法来追踪重定向
|
# 可以使用响应对象的history方法来追踪重定向, Response.history 是一个Response对象的列表, 按照从最老到最近的请求进行排序
|
||||||
# Response.history 是一个 Response 对象的列表, 为了完成请求而创建了这些对象. 这个对象列表按照从最老到最近的请求进行排序
|
r = requests.get("http://github.com", allow_redirects=True)
|
||||||
r = requests.get("http://github.com")
|
print(r.status_code) # 200
|
||||||
print(r.status_code) # 200
|
print(r.history) # [<Response [301]>]
|
||||||
print(r.history) # [<Response [301]>]
|
|
||||||
|
|
||||||
# 如果你使用的是GET、OPTIONS、POST、PUT、PATCH 或者 DELETE, 那么你可以通过 allow_redirects 参数禁用重定向处理
|
|
||||||
r = requests.get("http://github.com", allow_redirects=False)
|
r = requests.get("http://github.com", allow_redirects=False)
|
||||||
print(r.status_code) # 301
|
print(r.status_code) # 301
|
||||||
print(r.history) # []
|
print(r.history) # []
|
||||||
|
|
||||||
# 如果你使用了HEAD, 你也可以启用重定向
|
|
||||||
r = requests.head("http://github.com", allow_redirects=True)
|
|
||||||
print(r.history) # [<Response [301]>]
|
|
||||||
|
|
||||||
# 超时, 设置timeout参数
|
# 超时, 设置timeout参数
|
||||||
requests.get("http://github.com", timeout=0.001)
|
requests.get("http://github.com", timeout=0.001)
|
||||||
|
@ -164,10 +169,10 @@ requests.get("http://github.com", timeout=0.001)
|
||||||
|
|
||||||
# 注意: timeout仅对连接过程有效, 与响应体的下载无关
|
# 注意: timeout仅对连接过程有效, 与响应体的下载无关
|
||||||
# timeout并不是整个下载响应的时间限制, 而是如果服务器在timeout秒内没有应答, 将会引发一个异常
|
# timeout并不是整个下载响应的时间限制, 而是如果服务器在timeout秒内没有应答, 将会引发一个异常
|
||||||
# 更精确地说, 是在 timeout 秒内没有从基础套接字上接收到任何字节的数据时
|
# 更精确地说, 是在timeout秒内没有从基础套接字上接收到任何字节的数据时
|
||||||
requests.get("https://github.com", timeout=5)
|
requests.get("https://github.com", timeout=5)
|
||||||
# 这一 timeout 值将会用作 connect 和 read 二者的 timeout
|
|
||||||
# 如果要分别制定, 就传入一个元组
|
# 上边的timeout值将会用作 connect 和 read 二者的timeout, 如果要分别制定, 就传入一个元组
|
||||||
requests.get("https://github.com", timeout=(3.05, 27))
|
requests.get("https://github.com", timeout=(3.05, 27))
|
||||||
|
|
||||||
# 错误与异常: 遇到网络问题(如: DNS 查询失败、拒绝连接等)时, Requests 会抛出一个 ConnectionError 异常
|
# 错误与异常: 遇到网络问题(如: DNS 查询失败、拒绝连接等)时, Requests 会抛出一个 ConnectionError 异常
|
||||||
|
@ -176,6 +181,16 @@ requests.get("https://github.com", timeout=(3.05, 27))
|
||||||
# 若请求超过了设定的最大重定向次数, 则会抛出一个 TooManyRedirects 异常
|
# 若请求超过了设定的最大重定向次数, 则会抛出一个 TooManyRedirects 异常
|
||||||
# 所有Requests显式抛出的异常都继承自 requests.exceptions.RequestException
|
# 所有Requests显式抛出的异常都继承自 requests.exceptions.RequestException
|
||||||
|
|
||||||
|
# 所有异常
|
||||||
|
# exception requests.RequestException(*args, **kwargs): There was an ambiguous exception that occurred while handling your request.
|
||||||
|
# exception requests.ConnectionError(*args, **kwargs): A Connection error occurred.
|
||||||
|
# exception requests.HTTPError(*args, **kwargs): An HTTP error occurred.
|
||||||
|
# exception requests.URLRequired(*args, **kwargs): A valid URL is required to make a request.
|
||||||
|
# exception requests.TooManyRedirects(*args, **kwargs): Too many redirects.
|
||||||
|
# exception requests.ConnectTimeout(*args, **kwargs): The request timed out while trying to connect to the remote server.
|
||||||
|
# exception requests.ReadTimeout(*args, **kwargs): The server did not send any data in the allotted amount of time.
|
||||||
|
# exception requests.Timeout(*args, **kwargs): The request timed out.
|
||||||
|
|
||||||
# SSL证书验证, verify设置为True表示检查证书, 设置为False表示忽略证书
|
# SSL证书验证, verify设置为True表示检查证书, 设置为False表示忽略证书
|
||||||
requests.get("https://kennethreitz.com", verify=True) # 未设置SSL证书, 抛出异常
|
requests.get("https://kennethreitz.com", verify=True) # 未设置SSL证书, 抛出异常
|
||||||
# requests.exceptions.SSLError: hostname "kennethreitz.com" doesn"t match either of "*.herokuapp.com", "herokuapp.com"
|
# requests.exceptions.SSLError: hostname "kennethreitz.com" doesn"t match either of "*.herokuapp.com", "herokuapp.com"
|
||||||
|
@ -217,4 +232,4 @@ proxies = {
|
||||||
requests.get("http://example.org", proxies=proxies)
|
requests.get("http://example.org", proxies=proxies)
|
||||||
|
|
||||||
# 关闭InsecurePlatformWarning
|
# 关闭InsecurePlatformWarning
|
||||||
requests.packages.urllib3.disable_warnings()
|
# requests.packages.urllib3.disable_warnings()
|
||||||
|
|
Loading…
Reference in New Issue