requests库高级用法

桃扇骨 2022-01-11 05:23 315阅读 0赞

# 会话对象 #

> > s = requests.Session()  
> > s.get(‘[http://httpbin.org/cookies/set/sessioncookie/123456789][http_httpbin.org_cookies_set_sessioncookie_123456789]’)  
> > r = s.get(“[http://httpbin.org/cookies][http_httpbin.org_cookies]”)  
> > print(r.text)

> > s = requests.Session()  
> > s.auth = (‘user’, ‘pass’)  
> > s.headers.update(\{‘x-test’: ‘true’\})  
> > \#both ‘x-test’ and ‘x-test2’ are sent  
> > s.get(‘[http://httpbin.org/headers][http_httpbin.org_headers]’, headers=\{‘x-test2’: ‘true’\})

> > s = requests.Session()  
> > r = s.get(‘[http://httpbin.org/cookies][http_httpbin.org_cookies]’, cookies=\{‘from-my’: ‘browser’\})  
> > print(r.text)  
> > \#’\{“cookies”: \{“from-my”: “browser”\}\}’  
> > r = s.get(‘[http://httpbin.org/cookies][http_httpbin.org_cookies]’)  
> > print(r.text)  
> > \#’\{“cookies”: \{\}\}’

> > with requests.Session() as s:  
> > s.get(‘[http://httpbin.org/cookies/set/sessioncookie/123456789][http_httpbin.org_cookies_set_sessioncookie_123456789]’)

# 请求与响应对象 #

> > r = requests.get(‘[http://en.wikipedia.org/wiki/Monty\_Python][http_en.wikipedia.org_wiki_Monty_Python]’)  
> > r.headers  
> > \{‘content-length’: ‘56170’, ‘x-content-type-options’: ‘nosniff’, ‘x-cache’:  
> > ‘HIT from cp1006.eqiad.wmnet, MISS from cp1010.eqiad.wmnet’, ‘content-encoding’:  
> > ‘gzip’, ‘age’: ‘3080’, ‘content-language’: ‘en’, ‘vary’: ‘Accept-Encoding,Cookie’,  
> > ‘server’: ‘Apache’, ‘last-modified’: ‘Wed, 13 Jun 2012 01:33:50 GMT’,  
> > ‘connection’: ‘close’, ‘cache-control’: ‘private, s-maxage=0, max-age=0,  
> > must-revalidate’, ‘date’: ‘Thu, 14 Jun 2012 12:59:39 GMT’, ‘content-type’:  
> > ‘text/html; charset=UTF-8’, ‘x-cache-lookup’: ‘HIT from cp1006.eqiad.wmnet:3128,  
> > MISS from cp1010.eqiad.wmnet:80’\}

# 准备的请求 （Prepared Request） #

from requests import Request, Session
    
    s = Session()
    req = Request('GET', url,
        data=data,
        headers=header
    )
    prepped = req.prepare()
    
    # do something with prepped.body
    # do something with prepped.headers
    
    resp = s.send(prepped,
        stream=stream,
        verify=verify,
        proxies=proxies,
        cert=cert,
        timeout=timeout
    )
    
    print(resp.status_code)

from requests import Request, Session
    
    s = Session()
    req = Request('GET',  url,
        data=data
        headers=headers
    )
    
    prepped = s.prepare_request(req)
    
    # do something with prepped.body
    # do something with prepped.headers
    
    resp = s.send(prepped,
        stream=stream,
        verify=verify,
        proxies=proxies,
        cert=cert,
        timeout=timeout
    )
    
    print(resp.status_code)

# SSL 证书验证 #

> > requests.get(‘[https://requestb.in][https_requestb.in]’)  
> > requests.exceptions.SSLError: hostname ‘[requestb.in][]’ doesn’t match either of ‘\*.herokuapp.com’, ‘[herokuapp.com][]’

> > requests.get(‘[https://github.com][https_github.com]’, verify=True)  
> > <Response \[200\]>

> > requests.get(‘[https://github.com][https_github.com]’, verify=’/path/to/certfile’)

> > s = requests.Session()  
> > s.verify = ‘/path/to/certfile’

> > requests.get(‘[https://kennethreitz.org][https_kennethreitz.org]’, verify=False)  
> > <Response \[200\]>

# 客户端证书 #

> > requests.get(‘[https://kennethreitz.org][https_kennethreitz.org]’, cert=(’/path/client.cert’, ‘/path/client.key’))  
> > <Response \[200\]>

> > s = requests.Session()  
> > s.cert = ‘/path/client.cert’  
> > requests.get(‘[https://kennethreitz.org][https_kennethreitz.org]’,  
> > cert=’/wrong\_path/client.pem’)  
> > SSLError: \[Errno 336265225\] \_ssl.c:347: error:140B0009:SSL routines:SSL\_CTX\_use\_PrivateKey\_file:PEM lib

# CA 证书 #

> > Requests 默认附带了一套它信任的根证书，来自于 Mozilla trust store。然而它们在每次 Requests 更新时才会更新。这意味着如果你固定使用某一版本的 Requests，你的证书有可能已经 太旧了。

> > 从 Requests 2.4.0 版之后，如果系统中装了 certifi 包，Requests 会试图使用它里边的 证书。这样用户就可以在不修改代码的情况下更新他们的可信任证书。

> > 为了安全起见，我们建议你经常更新 certifi！

# 响应体内容工作流 #

> > tarball\_url = ‘[https://github.com/kennethreitz/requests/tarball/master][https_github.com_kennethreitz_requests_tarball_master]’  
> > r = requests.get(tarball\_url, stream=True)  
> > if int(r.headers\[‘content-length’\]) < TOO\_LONG:  
> > content = r.content  
> > …

# 流式上传 #

> > with open(‘massive-body’) as f:  
> > requests.post(‘[http://some.url/streamed][http_some.url_streamed]’, data=f)

# 块编码请求 #

def gen():
        yield 'hi'
        yield 'there'
    
    requests.post('http://some.url/chunked', data=gen())

# POST 多个分块编码的文件 #

> > url = ‘[http://httpbin.org/post][http_httpbin.org_post]’  
> > multiple\_files = \[  
> > (‘images’, (‘foo.png’, open(‘foo.png’, ‘rb’), ‘image/png’)),  
> > (‘images’, (‘bar.png’, open(‘bar.png’, ‘rb’), ‘image/png’))\]
> 
> > r = requests.post(url, files=multiple\_files)  
> > r.text  
> > \{  
> > …  
> > ‘files’: \{‘images’: ‘data:image/png;base64,iVBORw …’\}  
> > ‘Content-Type’: ‘multipart/form-data; boundary=3131623adb2043caaeb5538cc7aa0b3a’,  
> > …  
> > \}

# 事件挂钩 #

> > hooks=dict(response=print\_url)  
> > def print\_url(r, \*args, \*\*kwargs):  
> > print(r.url)  
> > requests.get(‘[http://httpbin.org][http_httpbin.org]’, hooks=dict(response=print\_url))  
> > [http://httpbin.org][http_httpbin.org]  
> > <Response \[200\]>

# 自定义身份验证 #

from requests.auth import AuthBase
    
    class PizzaAuth(AuthBase):
        """Attaches HTTP Pizza Authentication to the given Request object."""
        def __init__(self, username):
            # setup any auth-related data here
            self.username = username
    
        def __call__(self, r):
            # modify and return the request
            r.headers['X-Pizza'] = self.username
            return r
    >> requests.get('http://pizzabin.org/admin', auth=PizzaAuth('kenneth'))
    <Response [200]>

# 流式请求 #

import json
    import requests
    
    r = requests.get('http://httpbin.org/stream/20', stream=True)
    
    for line in r.iter_lines():
    
        # filter out keep-alive new lines
        if line:
            decoded_line = line.decode('utf-8')
            print(json.loads(decoded_line))
    
    
    r = requests.get('http://httpbin.org/stream/20', stream=True)
    
    if r.encoding is None:
        r.encoding = 'utf-8'
    
    for line in r.iter_lines(decode_unicode=True):
        if line:
            print(json.loads(line))

# 代理 #

import requests
    
    proxies = {
      "http": "http://10.10.1.10:3128",
      "https": "http://10.10.1.10:1080",
    }
    
    requests.get("http://example.org", proxies=proxies)

# SOCKS #

> > $ pip install requests\[socks\]  
> > proxies = \{  
> > ‘http’: ‘socks5://user:pass@host:port’,  
> > ‘https’: ‘socks5://user:pass@host:port’  
> > \}

# 合规性 #

> > Requests 符合所有相关的规范和 RFC，这样不会为用户造成不必要的困难。但这种对规范的考虑导致一些行为对于不熟悉相关规范的人来说看似有点奇怪。

# 编码方式 #

> > 当你收到一个响应时，Requests 会猜测响应的编码方式，用于在你调用 Response.text 方法时对响应进行解码。Requests 首先在 HTTP 头部检测是否存在指定的编码方式，如果不存在，则会使用 charade 来尝试猜测编码方式。

> > 只有当 HTTP 头部不存在明确指定的字符集，并且 Content-Type 头部字段包含 text 值之时， Requests 才不去猜测编码方式。在这种情况下， RFC 2616 指定默认字符集必须是 ISO-8859-1 。Requests 遵从这一规范。如果你需要一种不同的编码方式，你可以手动设置 Response.encoding 属性，或使用原始的 Response.content。

# HTTP动词 #

> > import requests  
> > r = requests.get(‘[https://api.github.com/repos/requests/requests/git/commits/a050faf084662f3a352dd1a941f2c7c9f886d4ad][https_api.github.com_repos_requests_requests_git_commits_a050faf084662f3a352dd1a941f2c7c9f886d4ad]’)  
> > if (r.status\_code == requests.codes.ok):  
> > … print r.headers\[‘content-type’\]  
> > …  
> > application/json; charset=utf-8
> 
> > commit\_data = r.json()
> 
> > print commit\_data.keys()  
> > \[u’committer’, u’author’, u’url’, u’tree’, u’sha’, u’parents’, u’message’\]
> 
> > print commit\_data\[u’committer’\]  
> > \{u’date’: u’2012-05-10T11:10:50-07:00’, u’email’: u’me@kennethreitz.com’, u’name’: u’Kenneth Reitz’\}
> 
> > print commit\_data\[u’message’\]  
> > makin’ history
> 
> > verbs = requests.options(r.url)  
> > verbs.status\_code  
> > 500
> 
> > verbs = requests.options(‘[http://a-good-website.com/api/cats][http_a-good-website.com_api_cats]’)  
> > print verbs.headers\[‘allow’\]  
> > GET,HEAD,POST,OPTIONS
> 
> > r=requests.get(‘[https://api.github.com/requests/kennethreitz/requests/issues/482][https_api.github.com_requests_kennethreitz_requests_issues_482]’)  
> > r.status\_code  
> > 200

> > issue = json.loads(r.text)  
> > print(issue\[u’title’\])  
> > Feature any http verb in docs
> 
> > print(issue\[u’comments’\])  
> > 3
> 
> > r = requests.get(r.url + u’/comments’)  
> > r.status\_code  
> > 200
> 
> > comments = r.json()  
> > print comments\[0\].keys()  
> > \[u’body’, u’url’, u’created\_at’, u’updated\_at’, u’user’, u’id’\]
> 
> > print comments\[2\]\[u’body’\]  
> > Probably in the “advanced” section
> 
> > print comments\[2\]\[u’user’\]\[u’login’\]  
> > kennethreitz
> 
> > body = json.dumps(\{u"body": u"Sounds great! I’ll get right on it!"\})  
> > url = u"[https://api.github.com/repos/requests/requests/issues/482/comments][https_api.github.com_repos_requests_requests_issues_482_comments]"  
> > r = requests.post(url=url, data=body)  
> > r.status\_code  
> > 404
> 
> > from requests.auth import HTTPBasicAuth  
> > auth = HTTPBasicAuth(‘fake@example.com’, ‘not\_a\_real\_password’)  
> > r = requests.post(url=url, data=body, auth=auth)  
> > r.status\_code  
> > 201
> 
> > content = r.json()  
> > print(content\[u’body’\])  
> > Sounds great! I’ll get right on it.
> 
> > print(content\[u"id"\])  
> > 5804413
> 
> > body = json.dumps(\{u"body": u"Sounds great! I’ll get right on it once I feed my cat."\})  
> > url = u"[https://api.github.com/repos/requests/requests/issues/comments/5804413][https_api.github.com_repos_requests_requests_issues_comments_5804413]"  
> > r = requests.patch(url=url, data=body, auth=auth)  
> > r.status\_code  
> > 200
> 
> > r = requests.head(url=url, auth=auth)  
> > print r.headers  
> > …  
> > ‘x-ratelimit-remaining’: ‘4995’  
> > ‘x-ratelimit-limit’: ‘5000’  
> > …

# 定制动词 #

> > r = requests.request(‘MKCOL’, url, data=data)  
> > r.status\_code  
> > 200 \# Assuming your call was correct

# 响应头链接字段 #

> > url = ‘[https://api.github.com/users/kennethreitz/repos?page=1&per\_page=10][https_api.github.com_users_kennethreitz_repos_page_1_per_page_10]’  
> > r = requests.head(url=url)  
> > r.headers\[‘link’\]  
> > ‘[https://api.github.com/users/kennethreitz/repos?page=2&per\_page=10][https_api.github.com_users_kennethreitz_repos_page_2_per_page_10]; rel=“next”, [https://api.github.com/users/kennethreitz/repos?page=6&per\_page=10][https_api.github.com_users_kennethreitz_repos_page_6_per_page_10]; rel=“last”’
> 
> > r.links\[“next”\]  
> > \{‘url’: ‘[https://api.github.com/users/kennethreitz/repos?page=2&per\_page=10][https_api.github.com_users_kennethreitz_repos_page_2_per_page_10]’, ‘rel’: ‘next’\}
> 
> > r.links\[“last”\]  
> > \{‘url’: ‘[https://api.github.com/users/kennethreitz/repos?page=7&per\_page=10][https_api.github.com_users_kennethreitz_repos_page_7_per_page_10]’, ‘rel’: ‘last’\}

# 传输适配器 #

> > s = requests.Session()  
> > s.mount(‘[http://www.github.com][http_www.github.com]’, MyAdapter())

# 示例: 指定的 SSL 版本 #

import ssl
    
    from requests.adapters import HTTPAdapter
    from requests.packages.urllib3.poolmanager import PoolManager
    
    
    class Ssl3HttpAdapter(HTTPAdapter):
        """"Transport adapter" that allows us to use SSLv3."""
    
        def init_poolmanager(self, connections, maxsize, block=False):
            self.poolmanager = PoolManager(num_pools=connections,
                                           maxsize=maxsize,
                                           block=block,
                                           ssl_version=ssl.PROTOCOL_SSLv3)

# 阻塞和非阻塞 #

> > 使用默认的传输适配器，Requests 不提供任何形式的非阻塞 IO。 Response.content 属性会阻塞，直到整个响应下载完成。如果你需要更多精细控制，该库的数据流功能（见 流式请求） 允许你每次接受少量的一部分响应，不过这些调用依然是阻塞式的。

> > 如果你对于阻塞式 IO 有所顾虑，还有很多项目可以供你使用，它们结合了 Requests 和 Python 的某个异步框架。典型的优秀例子是 grequests 和 requests-futures。

# 超时（timeout） #

> > r = requests.get(‘[https://github.com][https_github.com]’, timeout=5)  
> > r = requests.get(‘[https://github.com][https_github.com]’, timeout=(3.05, 27))  
> > r = requests.get(‘[https://github.com][https_github.com]’, timeout=None)

[http_httpbin.org_cookies_set_sessioncookie_123456789]: http://httpbin.org/cookies/set/sessioncookie/123456789
[http_httpbin.org_cookies]: http://httpbin.org/cookies
[http_httpbin.org_headers]: http://httpbin.org/headers
[http_en.wikipedia.org_wiki_Monty_Python]: http://en.wikipedia.org/wiki/Monty_Python
[https_requestb.in]: https://requestb.in
[requestb.in]: http://requestb.in
[herokuapp.com]: http://herokuapp.com
[https_github.com]: https://github.com
[https_kennethreitz.org]: https://kennethreitz.org
[https_github.com_kennethreitz_requests_tarball_master]: https://github.com/kennethreitz/requests/tarball/master
[http_some.url_streamed]: http://some.url/streamed
[http_httpbin.org_post]: http://httpbin.org/post
[http_httpbin.org]: http://httpbin.org
[https_api.github.com_repos_requests_requests_git_commits_a050faf084662f3a352dd1a941f2c7c9f886d4ad]: https://api.github.com/repos/requests/requests/git/commits/a050faf084662f3a352dd1a941f2c7c9f886d4ad
[http_a-good-website.com_api_cats]: http://a-good-website.com/api/cats
[https_api.github.com_requests_kennethreitz_requests_issues_482]: https://api.github.com/requests/kennethreitz/requests/issues/482
[https_api.github.com_repos_requests_requests_issues_482_comments]: https://api.github.com/repos/requests/requests/issues/482/comments
[https_api.github.com_repos_requests_requests_issues_comments_5804413]: https://api.github.com/repos/requests/requests/issues/comments/5804413
[https_api.github.com_users_kennethreitz_repos_page_1_per_page_10]: https://api.github.com/users/kennethreitz/repos?page=1&per_page=10
[https_api.github.com_users_kennethreitz_repos_page_2_per_page_10]: https://api.github.com/users/kennethreitz/repos?page=2&per_page=10
[https_api.github.com_users_kennethreitz_repos_page_6_per_page_10]: https://api.github.com/users/kennethreitz/repos?page=6&per_page=10
[https_api.github.com_users_kennethreitz_repos_page_7_per_page_10]: https://api.github.com/users/kennethreitz/repos?page=7&per_page=10
[http_www.github.com]: http://www.github.com