Python requests模塊基礎(chǔ)使用方法實例及高級應(yīng)用(自動登陸,抓取網(wǎng)頁源碼)實例詳解
1、Python requests模塊說明
requests是使用Apache2 licensed 許可證的HTTP庫。
用python編寫。
比urllib2模塊更簡潔。
Request支持HTTP連接保持和連接池,支持使用cookie保持會話,支持文件上傳,支持自動響應(yīng)內(nèi)容的編碼,支持國際化的URL和POST數(shù)據(jù)自動編碼。
在python內(nèi)置模塊的基礎(chǔ)上進(jìn)行了高度的封裝,從而使得python進(jìn)行網(wǎng)絡(luò)請求時,變得人性化,使用Requests可以輕而易舉的完成瀏覽器可有的任何操作。
現(xiàn)代,國際化,友好。
requests會自動實現(xiàn)持久連接keep-alive
2、Python requests模塊基礎(chǔ)入門
1)導(dǎo)入模塊
import requests
2)發(fā)送請求的簡潔
示例代碼:獲取一個網(wǎng)頁(個人github)
import requests
r = requests.get('https://github.com/Ranxf') # 最基本的不帶參數(shù)的get請求
r1 = requests.get(url='http://dict.baidu.com/s', params={'wd': 'python'}) # 帶參數(shù)的get請求
我們還可以使用requests模塊其它請求方法
1 requests.get(‘https://github.com/timeline.json') # GET請求
2 requests.post(“http://httpbin.org/post”) # POST請求
3 requests.put(“http://httpbin.org/put”) # PUT請求
4 requests.delete(“http://httpbin.org/delete”) # DELETE請求
5 requests.head(“http://httpbin.org/get”) # HEAD請求
6 requests.options(“http://httpbin.org/get” ) # OPTIONS請求
3)為url傳遞參數(shù)
>>> url_params = {'key':'value'} # 字典傳遞參數(shù),如果值為None的鍵不會被添加到url中
>>> r = requests.get('your url',params = url_params)
>>> print(r.url)
your url?key=value
4)響應(yīng)的內(nèi)容
r.encoding #獲取當(dāng)前的編碼
r.encoding = 'utf-8' #設(shè)置編碼
r.text #以encoding解析返回內(nèi)容。字符串方式的響應(yīng)體,會自動根據(jù)響應(yīng)頭部的字符編碼進(jìn)行解碼。
r.content #以字節(jié)形式(二進(jìn)制)返回。字節(jié)方式的響應(yīng)體,會自動為你解碼 gzip 和 deflate 壓縮。
r.headers #以字典對象存儲服務(wù)器響應(yīng)頭,但是這個字典比較特殊,字典鍵不區(qū)分大小寫,若鍵不存在則返回None
r.status_code #響應(yīng)狀態(tài)碼
r.raw #返回原始響應(yīng)體,也就是 urllib 的 response 對象,使用 r.raw.read()
r.ok # 查看r.ok的布爾值便可以知道是否登陸成功
#*特殊方法*#
r.json() #Requests中內(nèi)置的JSON解碼器,以json形式返回,前提返回的內(nèi)容確保是json格式的,不然解析出錯會拋異常
r.raise_for_status() #失敗請求(非200響應(yīng))拋出異常
post發(fā)送json請求:
import requests
import json
r = requests.post('https://api.github.com/some/endpoint', data=json.dumps({'some': 'data'}))
print(r.json())
5)定制頭和cookie信息
header = {'user-agent': 'my-app/0.0.1''}
cookie = {'key':'value'}
r = requests.get/post('your url',headers=header,cookies=cookie)
data = {'some': 'data'}
headers = {'content-type': 'application/json',
'User-Agent': 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:22.0) Gecko/20100101 Firefox/22.0'}
r = requests.post('https://api.github.com/some/endpoint', data=data, headers=headers)
print(r.text)
6)響應(yīng)狀態(tài)碼
使用requests方法后,會返回一個response對象,其存儲了服務(wù)器響應(yīng)的內(nèi)容,如上實例中已經(jīng)提到的 r.text、r.status_code……
獲取文本方式的響應(yīng)體實例:當(dāng)你訪問 r.text 之時,會使用其響應(yīng)的文本編碼進(jìn)行解碼,并且你可以修改其編碼讓 r.text 使用自定義的編碼進(jìn)行解碼。
r = requests.get('http://www.itwhy.org')
print(r.text, '\n{}\n'.format('*'*79), r.encoding)
r.encoding = 'GBK'
print(r.text, '\n{}\n'.format('*'*79), r.encoding)
示例代碼:
import requests
r = requests.get('https://github.com/Ranxf') # 最基本的不帶參數(shù)的get請求
print(r.status_code) # 獲取返回狀態(tài)
r1 = requests.get(url='http://dict.baidu.com/s', params={'wd': 'python'}) # 帶參數(shù)的get請求
print(r1.url)
print(r1.text) # 打印解碼后的返回數(shù)據(jù)
運(yùn)行結(jié)果:
/usr/bin/python3.5 /home/rxf/python3_1000/1000/python3_server/python3_requests/demo1.py
200
http://dict.baidu.com/s?wd=python
…………
Process finished with exit code 0
r.status_code #如果不是200,可以使用 r.raise_for_status() 拋出異常
7)響應(yīng)
r.headers #返回字典類型,頭信息
r.requests.headers #返回發(fā)送到服務(wù)器的頭信息
r.cookies #返回cookie
r.history #返回重定向信息,當(dāng)然可以在請求是加上allow_redirects = false 阻止重定向
8)超時
r = requests.get('url',timeout=1) #設(shè)置秒數(shù)超時,僅對于連接有效
9)會話對象,能夠跨請求保持某些參數(shù)
s = requests.Session()
s.auth = ('auth','passwd')
s.headers = {'key':'value'}
r = s.get('url')
r1 = s.get('url1')
10)代理
proxies = {'http':'ip1','https':'ip2' }
requests.get('url',proxies=proxies)
匯總:
# HTTP請求類型
# get類型
r = requests.get('https://github.com/timeline.json')
# post類型
r = requests.post("http://m.ctrip.com/post")
# put類型
r = requests.put("http://m.ctrip.com/put")
# delete類型
r = requests.delete("http://m.ctrip.com/delete")
# head類型
r = requests.head("http://m.ctrip.com/head")
# options類型
r = requests.options("http://m.ctrip.com/get")
# 獲取響應(yīng)內(nèi)容
print(r.content) #以字節(jié)的方式去顯示,中文顯示為字符
print(r.text) #以文本的方式去顯示
#URL傳遞參數(shù)
payload = {'keyword': '香港', 'salecityid': '2'}
r = requests.get("http://m.ctrip.com/webapp/tourvisa/visa_list", params=payload)
print(r.url) #示例為http://m.ctrip.com/webapp/tourvisa/visa_list?salecityid=2&keyword=香港
#獲取/修改網(wǎng)頁編碼
r = requests.get('https://github.com/timeline.json')
print (r.encoding)
#json處理
r = requests.get('https://github.com/timeline.json')
print(r.json()) # 需要先import json
# 定制請求頭
url = 'http://m.ctrip.com'
headers = {'User-Agent' : 'Mozilla/5.0 (Linux; Android 4.2.1; en-us; Nexus 4 Build/JOP40D) AppleWebKit/535.19 (KHTML, like Gecko) Chrome/18.0.1025.166 Mobile Safari/535.19'}
r = requests.post(url, headers=headers)
print (r.request.headers)
#復(fù)雜post請求
url = 'http://m.ctrip.com'
payload = {'some': 'data'}
r = requests.post(url, data=json.dumps(payload)) #如果傳遞的payload是string而不是dict,需要先調(diào)用dumps方法格式化一下
# post多部分編碼文件
url = 'http://m.ctrip.com'
files = {'file': open('report.xls', 'rb')}
r = requests.post(url, files=files)
# 響應(yīng)狀態(tài)碼
r = requests.get('http://m.ctrip.com')
print(r.status_code)
# 響應(yīng)頭
r = requests.get('http://m.ctrip.com')
print (r.headers)
print (r.headers['Content-Type'])
print (r.headers.get('content-type')) #訪問響應(yīng)頭部分內(nèi)容的兩種方式
# Cookies
url = 'http://example.com/some/cookie/setting/url'
r = requests.get(url)
r.cookies['example_cookie_name'] #讀取cookies
url = 'http://m.ctrip.com/cookies'
cookies = dict(cookies_are='working')
r = requests.get(url, cookies=cookies) #發(fā)送cookies
#設(shè)置超時時間
r = requests.get('http://m.ctrip.com', timeout=0.001)
#設(shè)置訪問代理
proxies = {
"http": "http://10.10.1.10:3128",
"https": "http://10.10.1.100:4444",
}
r = requests.get('http://m.ctrip.com', proxies=proxies)
#如果代理需要用戶名和密碼,則需要這樣:
proxies = {
"http": "http://user:pass@10.10.1.10:3128/",
}
# HTTP請求類型
# get類型
r = requests.get('https://github.com/timeline.json')
# post類型
r = requests.post("http://m.ctrip.com/post")
# put類型
r = requests.put("http://m.ctrip.com/put")
# delete類型
r = requests.delete("http://m.ctrip.com/delete")
# head類型
r = requests.head("http://m.ctrip.com/head")
# options類型
r = requests.options("http://m.ctrip.com/get")
# 獲取響應(yīng)內(nèi)容
print(r.content) #以字節(jié)的方式去顯示,中文顯示為字符
print(r.text) #以文本的方式去顯示
#URL傳遞參數(shù)
payload = {'keyword': '香港', 'salecityid': '2'}
r = requests.get("http://m.ctrip.com/webapp/tourvisa/visa_list", params=payload)
print(r.url) #示例為http://m.ctrip.com/webapp/tourvisa/visa_list?salecityid=2&keyword=香港
#獲取/修改網(wǎng)頁編碼
r = requests.get('https://github.com/timeline.json')
print (r.encoding)
#json處理
r = requests.get('https://github.com/timeline.json')
print(r.json()) # 需要先import json
# 定制請求頭
url = 'http://m.ctrip.com'
headers = {'User-Agent' : 'Mozilla/5.0 (Linux; Android 4.2.1; en-us; Nexus 4 Build/JOP40D) AppleWebKit/535.19 (KHTML, like Gecko) Chrome/18.0.1025.166 Mobile Safari/535.19'}
r = requests.post(url, headers=headers)
print (r.request.headers)
#復(fù)雜post請求
url = 'http://m.ctrip.com'
payload = {'some': 'data'}
r = requests.post(url, data=json.dumps(payload)) #如果傳遞的payload是string而不是dict,需要先調(diào)用dumps方法格式化一下
# post多部分編碼文件
url = 'http://m.ctrip.com'
files = {'file': open('report.xls', 'rb')}
r = requests.post(url, files=files)
# 響應(yīng)狀態(tài)碼
r = requests.get('http://m.ctrip.com')
print(r.status_code)
# 響應(yīng)頭
r = requests.get('http://m.ctrip.com')
print (r.headers)
print (r.headers['Content-Type'])
print (r.headers.get('content-type')) #訪問響應(yīng)頭部分內(nèi)容的兩種方式
# Cookies
url = 'http://example.com/some/cookie/setting/url'
r = requests.get(url)
r.cookies['example_cookie_name'] #讀取cookies
url = 'http://m.ctrip.com/cookies'
cookies = dict(cookies_are='working')
r = requests.get(url, cookies=cookies) #發(fā)送cookies
#設(shè)置超時時間
r = requests.get('http://m.ctrip.com', timeout=0.001)
#設(shè)置訪問代理
proxies = {
"http": "http://10.10.1.10:3128",
"https": "http://10.10.1.100:4444",
}
r = requests.get('http://m.ctrip.com', proxies=proxies)
#如果代理需要用戶名和密碼,則需要這樣:
proxies = {
"http": "http://user:pass@10.10.1.10:3128/",
}
3、示例代碼
GET請求
# 1、無參數(shù)實例
import requests
ret = requests.get('https://github.com/timeline.json')
print(ret.url)
print(ret.text)
# 2、有參數(shù)實例
import requests
payload = {'key1': 'value1', 'key2': 'value2'}
ret = requests.get("http://httpbin.org/get", params=payload)
print(ret.url)
print(ret.text)
POST請求
# 1、基本POST實例
import requests
payload = {'key1': 'value1', 'key2': 'value2'}
ret = requests.post("http://httpbin.org/post", data=payload)
print(ret.text)
# 2、發(fā)送請求頭和數(shù)據(jù)實例
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)
請求參數(shù)
def request(method, url, **kwargs):
"""Constructs and sends a :class:`Request <Request>`.
:param method: method for the new :class:`Request` object.
:param url: URL for the new :class:`Request` object.
:param params: (optional) Dictionary or bytes to be sent in the query string for the :class:`Request`.
:param data: (optional) Dictionary, bytes, or file-like object to send in the body of the :class:`Request`.
:param json: (optional) json data to send in the body of the :class:`Request`.
:param headers: (optional) Dictionary of HTTP Headers to send with the :class:`Request`.
:param cookies: (optional) Dict or CookieJar object to send with the :class:`Request`.
:param files: (optional) Dictionary of ``'name': file-like-objects`` (or ``{'name': file-tuple}``) for multipart encoding upload.
``file-tuple`` can be a 2-tuple ``('filename', fileobj)``, 3-tuple ``('filename', fileobj, 'content_type')``
or a 4-tuple ``('filename', fileobj, 'content_type', custom_headers)``, where ``'content-type'`` is a string
defining the content type of the given file and ``custom_headers`` a dict-like object containing additional headers
to add for the file.
:param auth: (optional) Auth tuple to enable Basic/Digest/Custom HTTP Auth.
:param timeout: (optional) How long to wait for the server to send data
before giving up, as a float, or a :ref:`(connect timeout, read
timeout) <timeouts>` tuple.
:type timeout: float or tuple
:param allow_redirects: (optional) Boolean. Set to True if POST/PUT/DELETE redirect following is allowed.
:type allow_redirects: bool
:param proxies: (optional) Dictionary mapping protocol to the URL of the proxy.
:param verify: (optional) whether the SSL cert will be verified. A CA_BUNDLE path can also be provided. Defaults to ``True``.
:param stream: (optional) if ``False``, the response content will be immediately downloaded.
:param cert: (optional) if String, path to ssl client cert file (.pem). If Tuple, ('cert', 'key') pair.
:return: :class:`Response <Response>` object
:rtype: requests.Response
Usage::
>>> import requests
>>> req = requests.request('GET', 'http://httpbin.org/get')
<Response [200]>
參數(shù)示例代碼
def param_method_url():
# requests.request(method='get', url='http://127.0.0.1:8000/test/')
# requests.request(method='post', url='http://127.0.0.1:8000/test/')
pass
def param_param():
# - 可以是字典
# - 可以是字符串
# - 可以是字節(jié)(ascii編碼以內(nèi))
# requests.request(method='get',
# url='http://127.0.0.1:8000/test/',
# params={'k1': 'v1', 'k2': '水電費(fèi)'})
# requests.request(method='get',
# url='http://127.0.0.1:8000/test/',
# params="k1=v1&k2=水電費(fèi)&k3=v3&k3=vv3")
# requests.request(method='get',
# url='http://127.0.0.1:8000/test/',
# params=bytes("k1=v1&k2=k2&k3=v3&k3=vv3", encoding='utf8'))
# 錯誤
# requests.request(method='get',
# url='http://127.0.0.1:8000/test/',
# params=bytes("k1=v1&k2=水電費(fèi)&k3=v3&k3=vv3", encoding='utf8'))
pass
def param_data():
# 可以是字典
# 可以是字符串
# 可以是字節(jié)
# 可以是文件對象
# requests.request(method='POST',
# url='http://127.0.0.1:8000/test/',
# data={'k1': 'v1', 'k2': '水電費(fèi)'})
# requests.request(method='POST',
# url='http://127.0.0.1:8000/test/',
# data="k1=v1; k2=v2; k3=v3; k3=v4"
# )
# requests.request(method='POST',
# url='http://127.0.0.1:8000/test/',
# data="k1=v1;k2=v2;k3=v3;k3=v4",
# headers={'Content-Type': 'application/x-www-form-urlencoded'}
# )
# requests.request(method='POST',
# url='http://127.0.0.1:8000/test/',
# data=open('data_file.py', mode='r', encoding='utf-8'), # 文件內(nèi)容是:k1=v1;k2=v2;k3=v3;k3=v4
# headers={'Content-Type': 'application/x-www-form-urlencoded'}
# )
pass
def param_json():
# 將json中對應(yīng)的數(shù)據(jù)進(jìn)行序列化成一個字符串,json.dumps(...)
# 然后發(fā)送到服務(wù)器端的body中,并且Content-Type是 {'Content-Type': 'application/json'}
requests.request(method='POST',
url='http://127.0.0.1:8000/test/',
json={'k1': 'v1', 'k2': '水電費(fèi)'})
def param_headers():
# 發(fā)送請求頭到服務(wù)器端
requests.request(method='POST',
url='http://127.0.0.1:8000/test/',
json={'k1': 'v1', 'k2': '水電費(fèi)'},
headers={'Content-Type': 'application/x-www-form-urlencoded'}
)
def param_cookies():
# 發(fā)送Cookie到服務(wù)器端
requests.request(method='POST',
url='http://127.0.0.1:8000/test/',
data={'k1': 'v1', 'k2': 'v2'},
cookies={'cook1': 'value1'},
)
# 也可以使用CookieJar(字典形式就是在此基礎(chǔ)上封裝)
from http.cookiejar import CookieJar
from http.cookiejar import Cookie
obj = CookieJar()
obj.set_cookie(Cookie(version=0, name='c1', value='v1', port=None, domain='', path='/', secure=False, expires=None,
discard=True, comment=None, comment_url=None, rest={'HttpOnly': None}, rfc2109=False,
port_specified=False, domain_specified=False, domain_initial_dot=False, path_specified=False)
)
requests.request(method='POST',
url='http://127.0.0.1:8000/test/',
data={'k1': 'v1', 'k2': 'v2'},
cookies=obj)
def param_files():
# 發(fā)送文件
# file_dict = {
# 'f1': open('readme', 'rb')
# }
# requests.request(method='POST',
# url='http://127.0.0.1:8000/test/',
# files=file_dict)
# 發(fā)送文件,定制文件名
# file_dict = {
# 'f1': ('test.txt', open('readme', 'rb'))
# }
# requests.request(method='POST',
# url='http://127.0.0.1:8000/test/',
# files=file_dict)
# 發(fā)送文件,定制文件名
# file_dict = {
# 'f1': ('test.txt', "hahsfaksfa9kasdjflaksdjf")
# }
# requests.request(method='POST',
# url='http://127.0.0.1:8000/test/',
# files=file_dict)
# 發(fā)送文件,定制文件名
# file_dict = {
# 'f1': ('test.txt', "hahsfaksfa9kasdjflaksdjf", 'application/text', {'k1': '0'})
# }
# requests.request(method='POST',
# url='http://127.0.0.1:8000/test/',
# files=file_dict)
pass
def param_auth():
from requests.auth import HTTPBasicAuth, HTTPDigestAuth
ret = requests.get('https://api.github.com/user', auth=HTTPBasicAuth('wupeiqi', 'sdfasdfasdf'))
print(ret.text)
# ret = requests.get('http://192.168.1.1',
# auth=HTTPBasicAuth('admin', 'admin'))
# ret.encoding = 'gbk'
# print(ret.text)
# ret = requests.get('http://httpbin.org/digest-auth/auth/user/pass', auth=HTTPDigestAuth('user', 'pass'))
# print(ret)
#
def param_timeout():
# ret = requests.get('http://google.com/', timeout=1)
# print(ret)
# ret = requests.get('http://google.com/', timeout=(5, 1))
# print(ret)
pass
def param_allow_redirects():
ret = requests.get('http://127.0.0.1:8000/test/', allow_redirects=False)
print(ret.text)
def param_proxies():
# proxies = {
# "http": "61.172.249.96:80",
# "https": "http://61.185.219.126:3128",
# }
# proxies = {'http://10.20.1.128': 'http://10.10.1.10:5323'}
# ret = requests.get("http://www.proxy#/Proxy", proxies=proxies)
# print(ret.headers)
# from requests.auth import HTTPProxyAuth
#
# proxyDict = {
# 'http': '77.75.105.165',
# 'https': '77.75.105.165'
# }
# auth = HTTPProxyAuth('username', 'mypassword')
#
# r = requests.get("http://www.google.com", proxies=proxyDict, auth=auth)
# print(r.text)
pass
def param_stream():
ret = requests.get('http://127.0.0.1:8000/test/', stream=True)
print(ret.content)
ret.close()
# from contextlib import closing
# with closing(requests.get('http://httpbin.org/get', stream=True)) as r:
# # 在此處理響應(yīng)。
# for i in r.iter_content():
# print(i)
def requests_session():
import requests
session = requests.Session()
### 1、首先登陸任何頁面,獲取cookie
i1 = session.get(url="http://dig.chouti.com/help/service")
### 2、用戶登陸,攜帶上一次的cookie,后臺對cookie中的 gpsd 進(jìn)行授權(quán)
i2 = session.post(
url="http://dig.chouti.com/login",
data={
'phone': "8615131255089",
'password': "xxxxxx",
'oneMonth': ""
}
)
i3 = session.post(
url="http://dig.chouti.com/link/vote?linksId=8589623",
)
print(i3.text)
json請求:
#! /usr/bin/python3
import requests
import json
class url_request():
def __init__(self):
''' init '''
if __name__ == '__main__':
heard = {'Content-Type': 'application/json'}
payload = {'CountryName': '中國',
'ProvinceName': '四川省',
'L1CityName': 'chengdu',
'L2CityName': 'yibing',
'TownName': '',
'Longitude': '107.33393',
'Latitude': '33.157131',
'Language': 'CN'}
r = requests.post("http://www.xxxxxx.com/CityLocation/json/LBSLocateCity", heards=heard, data=payload)
data = r.json()
if r.status_code!=200:
print('LBSLocateCity API Error' + str(r.status_code))
print(data['CityEntities'][0]['CityID']) # 打印返回json中的某個key的value
print(data['ResponseStatus']['Ack'])
print(json.dump(data, indent=4, sort_keys=True, ensure_ascii=False)) # 樹形打印json,ensure_ascii必須設(shè)為False否則中文會顯示為unicode
Xml請求:
#! /usr/bin/python3
import requests
class url_request():
def __init__(self):
"""init"""
if __name__ == '__main__':
heards = {'Content-type': 'text/xml'}
XML = '<?xml version="1.0" encoding="utf-8"?><soap:Envelope xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:soap="http://schemas.xmlsoap.org/soap/envelope/"><soap:Body><Request xmlns="http://tempuri.org/"><jme><JobClassFullName>WeChatJSTicket.JobWS.Job.JobRefreshTicket,WeChatJSTicket.JobWS</JobClassFullName><Action>RUN</Action><Param>1</Param><HostIP>127.0.0.1</HostIP><JobInfo>1</JobInfo><NeedParallel>false</NeedParallel></jme></Request></soap:Body></soap:Envelope>'
url = 'http://jobws.push.mobile.xxxxxxxx.com/RefreshWeiXInTokenJob/RefreshService.asmx'
r = requests.post(url=url, heards=heards, data=XML)
data = r.text
print(data)
狀態(tài)異常處理
import requests
URL = 'http://ip.taobao.com/service/getIpInfo.php' # 淘寶IP地址庫API
try:
r = requests.get(URL, params={'ip': '8.8.8.8'}, timeout=1)
r.raise_for_status() # 如果響應(yīng)狀態(tài)碼不是 200,就主動拋出異常
except requests.RequestException as e:
print(e)
else:
result = r.json()
print(type(result), result, sep='\n')
上傳文件
使用request模塊,也可以上傳文件,文件的類型會自動進(jìn)行處理:
import requests
url = 'http://127.0.0.1:8080/upload'
files = {'file': open('/home/rxf/test.jpg', 'rb')}
#files = {'file': ('report.jpg', open('/home/lyb/sjzl.mpg', 'rb'))} #顯式的設(shè)置文件名
r = requests.post(url, files=files)
print(r.text)
request更加方便的是,可以把字符串當(dāng)作文件進(jìn)行上傳:
import requests
url = 'http://127.0.0.1:8080/upload'
files = {'file': ('test.txt', b'Hello Requests.')} #必需顯式的設(shè)置文件名
r = requests.post(url, files=files)
print(r.text)
身份驗證
基本身份認(rèn)證(HTTP Basic Auth)
import requests
from requests.auth import HTTPBasicAuth
r = requests.get('https://httpbin.org/hidden-basic-auth/user/passwd', auth=HTTPBasicAuth('user', 'passwd'))
# r = requests.get('https://httpbin.org/hidden-basic-auth/user/passwd', auth=('user', 'passwd')) # 簡寫
print(r.json())
另一種非常流行的HTTP身份認(rèn)證形式是摘要式身份認(rèn)證,Requests對它的支持也是開箱即可用的:
requests.get(URL, auth=HTTPDigestAuth('user', 'pass')
Cookies與會話對象
如果某個響應(yīng)中包含一些Cookie,你可以快速訪問它們:
import requests
r = requests.get('http://www.google.com.hk/')
print(r.cookies['NID'])
print(tuple(r.cookies))
要想發(fā)送你的cookies到服務(wù)器,可以使用 cookies 參數(shù):
import requests
url = 'http://httpbin.org/cookies'
cookies = {'testCookies_1': 'Hello_Python3', 'testCookies_2': 'Hello_Requests'}
# 在Cookie Version 0中規(guī)定空格、方括號、圓括號、等于號、逗號、雙引號、斜杠、問號、@,冒號,分號等特殊符號都不能作為Cookie的內(nèi)容。
r = requests.get(url, cookies=cookies)
print(r.json())
會話對象讓你能夠跨請求保持某些參數(shù),最方便的是在同一個Session實例發(fā)出的所有請求之間保持cookies,且這些都是自動處理的,甚是方便。
下面就來一個真正的實例,如下是快盤簽到腳本:
import requests
headers = {'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
'Accept-Encoding': 'gzip, deflate, compress',
'Accept-Language': 'en-us;q=0.5,en;q=0.3',
'Cache-Control': 'max-age=0',
'Connection': 'keep-alive',
'User-Agent': 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:22.0) Gecko/20100101 Firefox/22.0'}
s = requests.Session()
s.headers.update(headers)
# s.auth = ('superuser', '123')
s.get('https://www.kuaipan.cn/account_login.htm')
_URL = 'http://www.kuaipan.cn/index.php'
s.post(_URL, params={'ac':'account', 'op':'login'},
data={'username':'****@foxmail.com', 'userpwd':'********', 'isajax':'yes'})
r = s.get(_URL, params={'ac':'zone', 'op':'taskdetail'})
print(r.json())
s.get(_URL, params={'ac':'common', 'op':'usersign'})
requests模塊抓取網(wǎng)頁源碼并保存到文件示例
這是一個基本的文件保存操作,但這里有幾個值得注意的問題:
1.安裝requests包,命令行輸入pip install requests即可自動安裝。很多人推薦使用requests,自帶的urllib.request也可以抓取網(wǎng)頁源碼
2.open方法encoding參數(shù)設(shè)為utf-8,否則保存的文件會出現(xiàn)亂碼。
3.如果直接在cmd中輸出抓取的內(nèi)容,會提示各種編碼錯誤,所以保存到文件查看。
4.with open方法是更好的寫法,可以自動操作完畢后釋放資源
Python requests模塊抽屜自動登錄
#! /urs/bin/python3
import requests
'''requests模塊抓取網(wǎng)頁源碼并保存到文件示例'''
html = requests.get("http://www.baidu.com")
with open('test.txt', 'w', encoding='utf-8') as f:
f.write(html.text)
'''讀取一個txt文件,每次讀取一行,并保存到另一個txt文件中的示例'''
ff = open('testt.txt', 'w', encoding='utf-8')
with open('test.txt', encoding="utf-8") as f:
for line in f:
ff.write(line)
ff.close()
因為在命令行中打印每次讀取一行的數(shù)據(jù),中文會出現(xiàn)編碼錯誤,所以每次讀取一行并保存到另一個文件,這樣來測試讀取是否正常。(注意open的時候制定encoding編碼方式)
Python requests模塊自動登陸實例:
#!/usr/bin/env python
# -*- coding:utf-8 -*-
import requests
# ############## 方式一 ##############
"""
# ## 1、首先登陸任何頁面,獲取cookie
i1 = requests.get(url="http://dig.chouti.com/help/service")
i1_cookies = i1.cookies.get_dict()
# ## 2、用戶登陸,攜帶上一次的cookie,后臺對cookie中的 gpsd 進(jìn)行授權(quán)
i2 = requests.post(
url="http://dig.chouti.com/login",
data={
'phone': "8615131255089",
'password': "xxooxxoo",
'oneMonth': ""
},
cookies=i1_cookies
)
# ## 3、點贊(只需要攜帶已經(jīng)被授權(quán)的gpsd即可)
gpsd = i1_cookies['gpsd']
i3 = requests.post(
url="http://dig.chouti.com/link/vote?linksId=8589523",
cookies={'gpsd': gpsd}
)
print(i3.text)
"""
# ############## 方式二 ##############
"""
import requests
session = requests.Session()
i1 = session.get(url="http://dig.chouti.com/help/service")
i2 = session.post(
url="http://dig.chouti.com/login",
data={
'phone': "8615131255089",
'password': "xxooxxoo",
'oneMonth': ""
}
)
i3 = session.post(
url="http://dig.chouti.com/link/vote?linksId=8589523"
)
print(i3.text)
"""
Python requests模塊github自動登錄
#!/usr/bin/env python
# -*- coding:utf-8 -*-
import requests
from bs4 import BeautifulSoup
# ############## 方式一 ##############
#
# # 1. 訪問登陸頁面,獲取 authenticity_token
# i1 = requests.get('https://github.com/login')
# soup1 = BeautifulSoup(i1.text, features='lxml')
# tag = soup1.find(name='input', attrs={'name': 'authenticity_token'})
# authenticity_token = tag.get('value')
# c1 = i1.cookies.get_dict()
# i1.close()
#
# # 1. 攜帶authenticity_token和用戶名密碼等信息,發(fā)送用戶驗證
# form_data = {
# "authenticity_token": authenticity_token,
# "utf8": "",
# "commit": "Sign in",
# "login": "wupeiqi@live.com",
# 'password': 'xxoo'
# }
#
# i2 = requests.post('https://github.com/session', data=form_data, cookies=c1)
# c2 = i2.cookies.get_dict()
# c1.update(c2)
# i3 = requests.get('https://github.com/settings/repositories', cookies=c1)
#
# soup3 = BeautifulSoup(i3.text, features='lxml')
# list_group = soup3.find(name='div', class_='listgroup')
#
# from bs4.element import Tag
#
# for child in list_group.children:
# if isinstance(child, Tag):
# project_tag = child.find(name='a', class_='mr-1')
# size_tag = child.find(name='small')
# temp = "項目:%s(%s); 項目路徑:%s" % (project_tag.get('href'), size_tag.string, project_tag.string, )
# print(temp)
# ############## 方式二 ##############
# session = requests.Session()
# # 1. 訪問登陸頁面,獲取 authenticity_token
# i1 = session.get('https://github.com/login')
# soup1 = BeautifulSoup(i1.text, features='lxml')
# tag = soup1.find(name='input', attrs={'name': 'authenticity_token'})
# authenticity_token = tag.get('value')
# c1 = i1.cookies.get_dict()
# i1.close()
#
# # 1. 攜帶authenticity_token和用戶名密碼等信息,發(fā)送用戶驗證
# form_data = {
# "authenticity_token": authenticity_token,
# "utf8": "",
# "commit": "Sign in",
# "login": "wupeiqi@live.com",
# 'password': 'xxoo'
# }
#
# i2 = session.post('https://github.com/session', data=form_data)
# c2 = i2.cookies.get_dict()
# c1.update(c2)
# i3 = session.get('https://github.com/settings/repositories')
#
# soup3 = BeautifulSoup(i3.text, features='lxml')
# list_group = soup3.find(name='div', class_='listgroup')
#
# from bs4.element import Tag
#
# for child in list_group.children:
# if isinstance(child, Tag):
# project_tag = child.find(name='a', class_='mr-1')
# size_tag = child.find(name='small')
# temp = "項目:%s(%s); 項目路徑:%s" % (project_tag.get('href'), size_tag.string, project_tag.string, )
# print(temp)
Python requests模塊知乎自動登錄
#!/usr/bin/env python
# -*- coding:utf-8 -*-
import time
import requests
from bs4 import BeautifulSoup
session = requests.Session()
i1 = session.get(
url='https://www.zhihu.com/#signin',
headers={
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.98 Safari/537.36',
}
)
soup1 = BeautifulSoup(i1.text, 'lxml')
xsrf_tag = soup1.find(name='input', attrs={'name': '_xsrf'})
xsrf = xsrf_tag.get('value')
current_time = time.time()
i2 = session.get(
url='https://www.zhihu.com/captcha.gif',
params={'r': current_time, 'type': 'login'},
headers={
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.98 Safari/537.36',
})
with open('zhihu.gif', 'wb') as f:
f.write(i2.content)
captcha = input('請打開zhihu.gif文件,查看并輸入驗證碼:')
form_data = {
"_xsrf": xsrf,
'password': 'xxooxxoo',
"captcha": 'captcha',
'email': '424662508@qq.com'
}
i3 = session.post(
url='https://www.zhihu.com/login/email',
data=form_data,
headers={
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.98 Safari/537.36',
}
)
i4 = session.get(
url='https://www.zhihu.com/settings/profile',
headers={
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.98 Safari/537.36',
}
)
soup4 = BeautifulSoup(i4.text, 'lxml')
tag = soup4.find(id='rename-section')
nick_name = tag.find('span',class_='name').string
print(nick_name)
Python requests模塊博客園自動登錄
#!/usr/bin/env python
# -*- coding:utf-8 -*-
import re
import json
import base64
import rsa
import requests
def js_encrypt(text):
b64der = 'MIGfMA0GCSqGSIb3DQEBAQUAA4GNADCBiQKBgQCp0wHYbg/NOPO3nzMD3dndwS0MccuMeXCHgVlGOoYyFwLdS24Im2e7YyhB0wrUsyYf0/nhzCzBK8ZC9eCWqd0aHbdgOQT6CuFQBMjbyGYvlVYU2ZP7kG9Ft6YV6oc9ambuO7nPZh+bvXH0zDKfi02prknrScAKC0XhadTHT3Al0QIDAQAB'
der = base64.standard_b64decode(b64der)
pk = rsa.PublicKey.load_pkcs1_openssl_der(der)
v1 = rsa.encrypt(bytes(text, 'utf8'), pk)
value = base64.encodebytes(v1).replace(b'\n', b'')
value = value.decode('utf8')
return value
session = requests.Session()
i1 = session.get('https://passport.cnblogs.com/user/signin')
rep = re.compile("'VerificationToken': '(.*)'")
v = re.search(rep, i1.text)
verification_token = v.group(1)
form_data = {
'input1': js_encrypt('wptawy'),
'input2': js_encrypt('asdfasdf'),
'remember': False
}
i2 = session.post(url='https://passport.cnblogs.com/user/signin',
data=json.dumps(form_data),
headers={
'Content-Type': 'application/json; charset=UTF-8',
'X-Requested-With': 'XMLHttpRequest',
'VerificationToken': verification_token}
)
i3 = session.get(url='https://i.cnblogs.com/EditDiary.aspx')
print(i3.text)
Python requests模塊拉勾網(wǎng)自動登錄
#!/usr/bin/env python
# -*- coding:utf-8 -*-
import requests
# 第一步:訪問登陸頁,拿到X_Anti_Forge_Token,X_Anti_Forge_Code
# 1、請求url:https://passport.lagou.com/login/login.html
# 2、請求方法:GET
# 3、請求頭:
# User-agent
r1 = requests.get('https://passport.lagou.com/login/login.html',
headers={
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36',
},
)
X_Anti_Forge_Token = re.findall("X_Anti_Forge_Token = '(.*?)'", r1.text, re.S)[0]
X_Anti_Forge_Code = re.findall("X_Anti_Forge_Code = '(.*?)'", r1.text, re.S)[0]
print(X_Anti_Forge_Token, X_Anti_Forge_Code)
# print(r1.cookies.get_dict())
# 第二步:登陸
# 1、請求url:https://passport.lagou.com/login/login.json
# 2、請求方法:POST
# 3、請求頭:
# cookie
# User-agent
# Referer:https://passport.lagou.com/login/login.html
# X-Anit-Forge-Code:53165984
# X-Anit-Forge-Token:3b6a2f62-80f0-428b-8efb-ef72fc100d78
# X-Requested-With:XMLHttpRequest
# 4、請求體:
# isValidate:true
# username:15131252215
# password:ab18d270d7126ea65915c50288c22c0d
# request_form_verifyCode:''
# submit:''
r2 = requests.post(
'https://passport.lagou.com/login/login.json',
headers={
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36',
'Referer': 'https://passport.lagou.com/login/login.html',
'X-Anit-Forge-Code': X_Anti_Forge_Code,
'X-Anit-Forge-Token': X_Anti_Forge_Token,
'X-Requested-With': 'XMLHttpRequest'
},
data={
"isValidate": True,
'username': '15131255089',
'password': 'ab18d270d7126ea65915c50288c22c0d',
'request_form_verifyCode': '',
'submit': ''
},
cookies=r1.cookies.get_dict()
)
print(r2.text)
更多關(guān)于Python requests模塊基礎(chǔ)使用方法請查看下面的相關(guān)鏈接
相關(guān)文章
Python腳本實現(xiàn)datax全量同步mysql到hive
這篇文章主要和大家分享一下mysql全量同步到hive自動生成json文件的python腳本,文中的示例代碼講解詳細(xì),有需要的小伙伴可以參加一下2024-10-10
用python修改excel表某一列內(nèi)容的操作方法
這篇文章主要介紹了用python修改excel表某一列內(nèi)容的操作代碼,在實現(xiàn)過程中用到openpyxl這個庫,要生成隨機(jī)數(shù)就要有random這個庫,具體代碼跟隨小編一起看看吧2021-06-06
Python Opencv提取圖片中某種顏色組成的圖形的方法
這篇文章主要介紹了Python Opencv提取圖片中某種顏色組成的圖形的方法,文中通過示例代碼介紹的非常詳細(xì),對大家的學(xué)習(xí)或者工作具有一定的參考學(xué)習(xí)價值,需要的朋友們下面隨著小編來一起學(xué)習(xí)學(xué)習(xí)吧2019-09-09

