requests and BeautifulSoup
阿新 • • 發佈:2018-12-13
requests
Python標準庫中提供了:urllib、urllib2、httplib等模組以供Http請求,但是,它的 API 太渣了。它是為另一個時代、另一個網際網路所建立的。它需要巨量的工作,甚至包括各種方法覆蓋,來完成最簡單的任務。
Requests 是使用 Apache2 Licensed 許可證的 基於Python開發的HTTP 庫,其在Python內建模組的基礎上進行了高度的封裝,從而使得Pythoner進行網路請求時,變得美好了許多,使用Requests可以輕而易舉的完成瀏覽器可有的任何操作。
1、GET請求
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 |
# 1、無引數例項
import
requests
ret
=
requests.get(
'https://github.com/timeline.json' )
print
ret.url
print
ret.text
# 2、有引數例項
import
requests
payload
=
{
'key1'
:
'value1'
,
'key2'
:
'value2'
}
ret
=
requests.get(
"http://httpbin.org/get"
, params
=
payload)
print
ret.url
print
ret.text
|
2、POST請求
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 |
# 1、基本POST例項
import
requests
payload
=
{
'key1'
:
'value1'
,
'key2'
:
'value2'
}
ret
=
requests.post(
"http://httpbin.org/post"
, data
=
payload)
print
ret.text
# 2、傳送請求頭和資料例項
import
requests
import
json
url
=
'https://api.github.com/some/endpoint'
payload
=
{
'some'
:
'data'
}
headers
=
{
'content-type'
:
'application/json'
}
ret
=
requests.post(url, data
=
json.dumps(payload), headers
=
headers)
print
ret.text
print
ret.cookies
|
3、其他請求
1 2 3 4 5 6 7 8 9 10 |
requests.get(url, params
=
None
,
*
*
kwargs)
requests.post(url, data
=
None
, json
=
None
,
*
*
kwargs)
requests.put(url, data
=
None
,
*
*
kwargs)
requests.head(url,
*
*
kwargs)
requests.delete(url,
*
*
kwargs)
requests.patch(url, data
=
None
,
*
*
kwargs)
requests.options(url,
*
*
kwargs)
# 以上方法均是在此方法的基礎上構建
requests.request(method, url,
*
*
kwargs)
|
4、更多引數
1 def request(method, url, **kwargs): 2 """Constructs and sends a :class:`Request <Request>`. 3 4 :param method: method for the new :class:`Request` object. 5 :param url: URL for the new :class:`Request` object. 6 :param params: (optional) Dictionary or bytes to be sent in the query string for the :class:`Request`. 7 :param data: (optional) Dictionary, bytes, or file-like object to send in the body of the :class:`Request`. 8 :param json: (optional) json data to send in the body of the :class:`Request`. 9 :param headers: (optional) Dictionary of HTTP Headers to send with the :class:`Request`. 10 :param cookies: (optional) Dict or CookieJar object to send with the :class:`Request`. 11 :param files: (optional) Dictionary of ``'name': file-like-objects`` (or ``{'name': file-tuple}``) for multipart encoding upload. 12 ``file-tuple`` can be a 2-tuple ``('filename', fileobj)``, 3-tuple ``('filename', fileobj, 'content_type')`` 13 or a 4-tuple ``('filename', fileobj, 'content_type', custom_headers)``, where ``'content-type'`` is a string 14 defining the content type of the given file and ``custom_headers`` a dict-like object containing additional headers 15 to add for the file. 16 :param auth: (optional) Auth tuple to enable Basic/Digest/Custom HTTP Auth. 17 :param timeout: (optional) How long to wait for the server to send data 18 before giving up, as a float, or a :ref:`(connect timeout, read 19 timeout) <timeouts>` tuple. 20 :type timeout: float or tuple 21 :param allow_redirects: (optional) Boolean. Set to True if POST/PUT/DELETE redirect following is allowed. 22 :type allow_redirects: bool 23 :param proxies: (optional) Dictionary mapping protocol to the URL of the proxy. 24 :param verify: (optional) whether the SSL cert will be verified. A CA_BUNDLE path can also be provided. Defaults to ``True``. 25 :param stream: (optional) if ``False``, the response content will be immediately downloaded. 26 :param cert: (optional) if String, path to ssl client cert file (.pem). If Tuple, ('cert', 'key') pair. 27 :return: :class:`Response <Response>` object 28 :rtype: requests.Response 29 30 Usage:: 31 32 >>> import requests 33 >>> req = requests.request('GET', 'http://httpbin.org/get') 34 <Response [200]> 35 """ 36 37 引數列表View Code
1 def param_method_url(): 2 # requests.request(method='get', url='http://127.0.0.1:8000/test/') 3 # requests.request(method='post', url='http://127.0.0.1:8000/test/') 4 pass 5 6 7 def param_param(): 8 # - 可以是字典 9 # - 可以是字串 10 # - 可以是位元組(ascii編碼以內) 11 12 # requests.request(method='get', 13 # url='http://127.0.0.1:8000/test/', 14 # params={'k1': 'v1', 'k2': '水電費'}) 15 16 # requests.request(method='get', 17 # url='http://127.0.0.1:8000/test/', 18 # params="k1=v1&k2=水電費&k3=v3&k3=vv3") 19 20 # requests.request(method='get', 21 # url='http://127.0.0.1:8000/test/', 22 # params=bytes("k1=v1&k2=k2&k3=v3&k3=vv3", encoding='utf8')) 23 24 # 錯誤 25 # requests.request(method='get', 26 # url='http://127.0.0.1:8000/test/', 27 # params=bytes("k1=v1&k2=水電費&k3=v3&k3=vv3", encoding='utf8')) 28 pass 29 30 31 def param_data(): 32 # 可以是字典 33 # 可以是字串 34 # 可以是位元組 35 # 可以是檔案物件 36 37 # requests.request(method='POST', 38 # url='http://127.0.0.1:8000/test/', 39 # data={'k1': 'v1', 'k2': '水電費'}) 40 41 # requests.request(method='POST', 42 # url='http://127.0.0.1:8000/test/', 43 # data="k1=v1; k2=v2; k3=v3; k3=v4" 44 # ) 45 46 # requests.request(method='POST', 47 # url='http://127.0.0.1:8000/test/', 48 # data="k1=v1;k2=v2;k3=v3;k3=v4", 49 # headers={'Content-Type': 'application/x-www-form-urlencoded'} 50 # ) 51 52 # requests.request(method='POST', 53 # url='http://127.0.0.1:8000/test/', 54 # data=open('data_file.py', mode='r', encoding='utf-8'), # 檔案內容是:k1=v1;k2=v2;k3=v3;k3=v4 55 # headers={'Content-Type': 'application/x-www-form-urlencoded'} 56 # ) 57 pass 58 59 60 def param_json(): 61 # 將json中對應的資料進行序列化成一個字串,json.dumps(...) 62 # 然後傳送到伺服器端的body中,並且Content-Type是 {'Content-Type': 'application/json'} 63 requests.request(method='POST', 64 url='http://127.0.0.1:8000/test/', 65 json={'k1': 'v1', 'k2': '水電費'}) 66 67 68 def param_headers(): 69 # 傳送請求頭到伺服器端 70 requests.request(method='POST', 71 url='http://127.0.0.1:8000/test/', 72 json={'k1': 'v1', 'k2': '水電費'}, 73 headers={'Content-Type': 'application/x-www-form-urlencoded'} 74 ) 75 76 77 def param_cookies(): 78 # 傳送Cookie到伺服器端 79 requests.request(method='POST', 80 url='http://127.0.0.1:8000/test/', 81 data={'k1': 'v1', 'k2': 'v2'}, 82 cookies={'cook1': 'value1'}, 83 ) 84 # 也可以使用CookieJar(字典形式就是在此基礎上封裝) 85 from http.cookiejar import CookieJar 86 from http.cookiejar import Cookie 87 88 obj = CookieJar() 89 obj.set_cookie(Cookie(version=0, name='c1', value='v1', port=None, domain='', path='/', secure=False, expires=None, 90 discard=True, comment=None, comment_url=None, rest={'HttpOnly': None}, rfc2109=False, 91 port_specified=False, domain_specified=False, domain_initial_dot=False, path_specified=False) 92 ) 93 requests.request(method='POST', 94 url='http://127.0.0.1:8000/test/', 95 data={'k1': 'v1', 'k2': 'v2'}, 96 cookies=obj) 97 98 99 def param_files(): 100 # 傳送檔案 101 # file_dict = { 102 # 'f1': open('readme', 'rb') 103 # } 104 # requests.request(method='POST', 105 # url='http://127.0.0.1:8000/test/', 106 # files=file_dict) 107 108 # 傳送檔案,定製檔名 109 # file_dict = { 110 # 'f1': ('test.txt', open('readme', 'rb')) 111 # } 112 # requests.request(method='POST', 113 # url='http://127.0.0.1:8000/test/', 114 # files=file_dict) 115 116 # 傳送檔案,定製檔名 117 # file_dict = { 118 # 'f1': ('test.txt', "hahsfaksfa9kasdjflaksdjf") 119 # } 120 # requests.request(method='POST', 121 # url='http://127.0.0.1:8000/test/', 122 # files=file_dict) 123 124 # 傳送檔案,定製檔名 125 # file_dict = { 126 # 'f1': ('test.txt', "hahsfaksfa9kasdjflaksdjf", 'application/text', {'k1': '0'}) 127 # } 128 # requests.request(method='POST', 129 # url='http://127.0.0.1:8000/test/', 130 # files=file_dict) 131 132 pass 133 134 135 def param_auth(): 136 from requests.auth import HTTPBasicAuth, HTTPDigestAuth 137 138 ret = requests.get('https://api.github.com/user', auth=HTTPBasicAuth('wupeiqi', 'sdfasdfasdf')) 139 print(ret.text) 140 141 # ret = requests.get('http://192.168.1.1', 142 # auth=HTTPBasicAuth('admin', 'admin')) 143 # ret.encoding = 'gbk' 144 # print(ret.text) 145 146 # ret = requests.get('http://httpbin.org/digest-auth/auth/user/pass', auth=HTTPDigestAuth('user', 'pass')) 147 # print(ret) 148 # 149 150 151 def param_timeout(): 152 # ret = requests.get('http://google.com/', timeout=1) 153 # print(ret) 154 155 # ret = requests.get('http://google.com/', timeout=(5, 1)) 156 # print(ret) 157 pass 158 159 160 def param_allow_redirects(): 161 ret = requests.get('http://127.0.0.1:8000/test/', allow_redirects=False) 162 print(ret.text) 163 164 165 def param_proxies(): 166 # proxies = { 167 # "http": "61.172.249.96:80", 168 # "https": "http://61.185.219.126:3128", 169 # } 170 171 # proxies = {'http://10.20.1.128': 'http://10.10.1.10:5323'} 172 173 # ret = requests.get("http://www.proxy360.cn/Proxy", proxies=proxies) 174 # print(ret.headers) 175 176 177 # from requests.auth import HTTPProxyAuth 178 # 179 # proxyDict = { 180 # 'http': '77.75.105.165', 181 # 'https': '77.75.105.165' 182 # } 183 # auth = HTTPProxyAuth('username', 'mypassword') 184 # 185 # r = requests.get("http://www.google.com", proxies=proxyDict, auth=auth) 186 # print(r.text) 187 188 pass 189 190 191 def param_stream(): 192 ret = requests.get('http://127.0.0.1:8000/test/', stream=True) 193 print(ret.content) 194 ret.close() 195 196 # from contextlib import closing 197 # with closing(requests.get('http://httpbin.org/get', stream=True)) as r: 198 # # 在此處理響應。 199 # for i in r.iter_content(): 200 # print(i) 201 202 203 def requests_session(): 204 import requests 205 206 session = requests.Session() 207 208 ### 1、首先登陸任何頁面,獲取cookie 209 210 i1 = session.get(url="http://dig.chouti.com/help/service") 211 212 ### 2、使用者登陸,攜帶上一次的cookie,後臺對cookie中的 gpsd 進行授權 213 i2 = session.post( 214 url="http://dig.chouti.com/login", 215 data={ 216 'phone': "8615131255089", 217 'password': "xxxxxx", 218 'oneMonth': "" 219 } 220 ) 221 222 i3 = session.post( 223 url="http://dig.chouti.com/link/vote?linksId=8589623", 224 ) 225 print(i3.text) 226 227 引數示例View Code
官方文件:http://cn.python-requests.org/zh_CN/latest/user/quickstart.html#id4
BeautifulSoup
BeautifulSoup是一個模組,該模組用於接收一個HTML或XML字串,然後將其進行格式化,之後遍可以使用他提供的方法進行快速查詢指定元素,從而使得在HTML或XML中查詢指定元素變得簡單。
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 |
from
bs4
import
BeautifulSoup
html_doc
=
"""
<html><head><title>The Dormouse's story</title></head>
<body>
asdf
<div class="title">
<b>The Dormouse's story總共</b>
<h1>f</h1>
</div>
<div class="story">Once upon a time there were three little sisters; and their names were
<a class="sister0" id="link1">Els<span>f</span>ie</a>,
<a href="http://example.com/lacie" class="sister" id="link2">Lacie</a> and
<a href="http://example.com/tillie" class="sister" id="link3">Tillie</a>;
and they lived at the bottom of a well.</div>
ad<br/>sf
<p class="story">...</p>
</body>
</html>
"""
soup
=
BeautifulSoup(html_doc, features
=
"lxml"
)
# 找到第一個a標籤
tag1
=
soup.find(name
=
'a'
)
# 找到所有的a標籤
tag2
=
soup.find_all(name
=
'a'
)
# 找到id=link2的標籤
tag3
=
soup.select(
'#link2'
)
|
安裝:
1 |
pip3 install beautifulsoup4
|
使用示例:
1 2 3 4 5 6 7 8 9 10 11 |
from
bs4
import
BeautifulSoup
html_doc
=
"""
<html><head><title>The Dormouse's story</title></head>
<body>
...
</body>
</html>
"""
soup
=
BeautifulSoup(html_doc, features
=
"lxml"
)
|
1. name,標籤名稱
1 2 3 4 5 |
# tag = soup.find('a')
# name = tag.name # 獲取
# print(name)
# tag.name = 'span' # 設定
# print(soup)
|
2. attr,標籤屬性
1 2 3 4 5 6 |
# tag = soup.find('a')
# attrs = tag.attrs # 獲取
# print(attrs)
# tag.attrs = {'ik':123} # 設定
# tag.attrs['id'] = 'iiiii' # 設定
# print(soup)
|
3. children,所有子標籤
1 2 |
# body = soup.find('body')
# v = body.children
|
4. children,所有子子孫孫標籤
1 2 |
# body = soup.find('body')
# v = body.descendants
|
5. clear,將標籤的所有子標籤全部清空(保留標籤名)
1 2 3 |
# tag = soup.find('body')
# tag.clear()
# print(soup)
|
6. decompose,遞迴的刪除所有的標籤
1 2 3 |
# body = soup.find('body')
# body.decompose()
# print(soup)
|
7. extract,遞迴的刪除所有的標籤,並獲取刪除的標籤
1 2 3 |
# body = soup.find('body')
# v = body.extract()
# print(soup)
|
8. decode,轉換為字串(含當前標籤);decode_contents(不含當前標籤)
1 2 3 4 |
# body = soup.find('body')
# v = body.decode()
# v = body.decode_contents()
# print(v)
|
9. encode,轉換為位元組(含當前標籤);encode_contents(不含當前標籤)
1 2 3 4 |
# body = soup.find('body')
# v = body.encode()
# v = body.encode_contents()
# print(v)
|
10. find,獲取匹配的第一個標籤
1 2 3 4 5 |
# tag = soup.find('a')
# print(tag)
# tag = soup.find(name='a', attrs={'class': 'sister'}, recursive=True, text='Lacie')
# tag = soup.find(name='a', class_='sister', recursive=True, text='Lacie')
# print(tag)
|
11. find_all,獲取匹配的所有標籤
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 |