python的requests模塊詳解


 

 原文鏈接:https://www.cnblogs.com/lanyinhao/p/9634742.html

 

1、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,支持自動響應內容的編碼,支持國際化的URL和POST數據自動編碼。

在python內置模塊的基礎上進行了高度的封裝,從而使得python進行網絡請求時,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。

現代,國際化,友好。

requests會自動實現持久連接keep-alive

2、基礎入門

1)導入模塊

import requests

2)發送請求的簡潔

  示例代碼:獲取一個網頁(個人github)

import requests

r = requests.get('https://github.com/Ranxf')       # 最基本的不帶參數的get請求
r1 = requests.get(url='http://dict.baidu.com/s', params={'wd': '小馬'})      # 帶參數的get請求

不帶參數:

 

 

 帶參數:

 

 

 

 

 

 

我們就可以使用該方式使用以下各種方法

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,#獲取請求的url(包含參數)

>>> url_params = {'key':'value'}       #    字典傳遞參數,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)響應的內容

復制代碼
r.encoding                       #獲取當前的編碼
r.encoding = 'utf-8'             #設置編碼
r.text                           #以encoding解析返回內容。字符串方式的響應體,會自動根據響應頭部的字符編碼進行解碼。
r.content                        #以字節形式(二進制)返回。字節方式的響應體,會自動為你解碼 gzip 和 deflate 壓縮。

r.headers                        #以字典對象存儲服務器響應頭,但是這個字典比較特殊,字典鍵不區分大小寫,若鍵不存在則返回None

r.status_code                     #響應狀態碼
r.raw                             #返回原始響應體,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中內置的JSON解碼器,以json形式返回,前提返回的內容確保是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)拋出異常
復制代碼

 

r.txt

 

 

r.content

 

 

 r.header

 

r.status_code

 

 

r.raw

 

 

 

 這是要請求的接口結果,視圖函數,以及requests模塊請求結果:

 

 

 

 

 

 

 

 

 假如返回的不是json格式:

 

 

 r.raise_for_status()

 

 

 

前端中文要正常顯示,這里要加參數

 

 

post發送json請求:

1 import requests
2 import json
3  
4 r = requests.post('https://api.github.com/some/endpoint', data=json.dumps({'some': 'data'}))
5 print(r.json())

視圖函數:

 

 

 get請求:

 

 

 post請求:

 

 

 

加參數的post請求

 

 

 

 

 

 

 

 

 

 

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)

 

 

 

 

 添加請求頭信息之后:

 

 

 

 

 修改請求內容類型為json,用戶使用火狐瀏覽器訪問

 

 

 

 

cookie放在cookies里沒成功,把鍵值對放到請求頭成功了。回頭研究一下,再

 

 

6)響應狀態碼

使用requests方法后,會返回一個response對象,其存儲了服務器響應的內容,如上實例中已經提到的 r.text、r.status_code……
獲取文本方式的響應體實例:當你訪問 r.text 之時,會使用其響應的文本編碼進行解碼,並且你可以修改其編碼讓 r.text 使用自定義的編碼進行解碼。

1 r = requests.get('http://www.itwhy.org')
2 print(r.text, '\n{}\n'.format('*'*79), r.encoding)
3 r.encoding = 'GBK'
4 print(r.text, '\n{}\n'.format('*'*79), r.encoding)

示例代碼:

復制代碼
1 import requests
2 
3 r = requests.get('https://github.com/Ranxf')       # 最基本的不帶參數的get請求
4 print(r.status_code)                               # 獲取返回狀態
5 r1 = requests.get(url='http://dict.baidu.com/s', params={'wd': 'python'})      # 帶參數的get請求
6 print(r1.url)
7 print(r1.text)        # 打印解碼后的返回數據
復制代碼

運行結果:

/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

r.headers                                  #返回字典類型,頭信息
r.requests.headers                         #返回發送到服務器的頭信息  #這個不清楚是個啥呢
r.cookies                                  #返回cookie
r.history                                  #返回重定向信息,當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)           #設置秒數超時,僅對於連接有效

 

 這邊設置超時時間1秒,但是響應時間是2秒,所以超時了,報錯讀取超時

9)會話對象,能夠跨請求保持某些參數

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:

復制代碼
# 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")

# 獲取響應內容
print(r.content) #以字節的方式去顯示,中文顯示為字符
print(r.text) #以文本的方式去顯示

#URL傳遞參數
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)

# 響應狀態碼
r = requests.get('http://m.ctrip.com')
print(r.status_code)
    
# 響應頭
r = requests.get('http://m.ctrip.com')
print (r.headers)
print (r.headers['Content-Type'])
print (r.headers.get('content-type')) #訪問響應頭部分內容的兩種方式
    
# 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) #發送cookies

#設置超時時間
r = requests.get('http://m.ctrip.com', timeout=0.001)

#設置訪問代理
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/",
}
復制代碼
復制代碼
# 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")

# 獲取響應內容
print(r.content) #以字節的方式去顯示,中文顯示為字符
print(r.text) #以文本的方式去顯示

#URL傳遞參數
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)

# 響應狀態碼
r = requests.get('http://m.ctrip.com')
print(r.status_code)
    
# 響應頭
r = requests.get('http://m.ctrip.com')
print (r.headers)
print (r.headers['Content-Type'])
print (r.headers.get('content-type')) #訪問響應頭部分內容的兩種方式
    
# 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) #發送cookies

#設置超時時間
r = requests.get('http://m.ctrip.com', timeout=0.001)

#設置訪問代理
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/",
}
復制代碼

其它:

3、示例代碼

GET請求

復制代碼
1 # 1、無參數實例
 2   
 3 import requests
 4   
 5 ret = requests.get('https://github.com/timeline.json')
 6   
 7 print(ret.url)
 8 print(ret.text)
 9   
10   
11   
12 # 2、有參數實例
13   
14 import requests
15   
16 payload = {'key1': 'value1', 'key2': 'value2'}
17 ret = requests.get("http://httpbin.org/get", params=payload)
18   
19 print(ret.url)
20 print(ret.text)
復制代碼

POST請求

復制代碼
# 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、發送請求頭和數據實例
  
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)
復制代碼

請求參數

  請求參數
  參數示例代碼

json請求:

復制代碼
#! /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必須設為False否則中文會顯示為unicode
復制代碼

Xml請求:

復制代碼
#! /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)
復制代碼

狀態異常處理

復制代碼
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()  # 如果響應狀態碼不是 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')
復制代碼

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行處理:

復制代碼
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'))}     #顯式的設置文件名
 
r = requests.post(url, files=files)
print(r.text)
復制代碼

request更加方便的是,可以把字符串當作文件進行上傳:

復制代碼
import requests
 
url = 'http://127.0.0.1:8080/upload'
files = {'file': ('test.txt', b'Hello Requests.')}     #必需顯式的設置文件名
 
r = requests.post(url, files=files)
print(r.text)
復制代碼

6) 身份驗證

基本身份認證(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身份認證形式是摘要式身份認證,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))

要想發送你的cookies到服務器,可以使用 cookies 參數:

復制代碼
import requests
 
url = 'http://httpbin.org/cookies'
cookies = {'testCookies_1': 'Hello_Python3', 'testCookies_2': 'Hello_Requests'}
# 在Cookie Version 0中規定空格、方括號、圓括號、等於號、逗號、雙引號、斜杠、問號、@,冒號,分號等特殊符號都不能作為Cookie的內容。
r = requests.get(url, cookies=cookies)
print(r.json())
復制代碼

會話對象讓你能夠跨請求保持某些參數,最方便的是在同一個Session實例發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:

復制代碼
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'})
復制代碼

requests模塊抓取網頁源碼並保存到文件示例

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也可以抓取網頁源碼

2.open方法encoding參數設為utf-8,否則保存的文件會出現亂碼。

3.如果直接在cmd中輸出抓取的內容,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

復制代碼
#! /urs/bin/python3
import requests

'''requests模塊抓取網頁源碼並保存到文件示例'''
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,並保存到另一個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()
復制代碼

因為在命令行中打印每次讀取一行的數據,中文會出現編碼錯誤,所以每次讀取一行並保存到另一個文件,這樣來測試讀取是否正常。(注意open的時候制定encoding編碼方式)

 

自動登陸"示例:

  抽屜新熱榜
復制代碼
#!/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)
復制代碼
復制代碼
#!/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,查看並輸入驗證碼:')
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)
復制代碼
復制代碼
#!/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)
復制代碼
復制代碼
#!/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)
復制代碼

 

參考:

http://cn.python-requests.org/zh_CN/latest/user/quickstart.html#id4

http://www.python-requests.org/en/master/

http://docs.python-requests.org/en/latest/user/quickstart/

https://www.cnblogs.com/tangdongchu/p/4229049.html#t0

http://www.cnblogs.com/wupeiqi/articles/6283017.html

 

 

 

 

 

 

 

 

 

 

 

 

 

參考鏈接:https://www.cnblogs.com/lanyinhao/p/9634742.html


免責聲明!

本站轉載的文章為個人學習借鑒使用,本站對版權不負任何法律責任。如果侵犯了您的隱私權益,請聯系本站郵箱yoyou2525@163.com刪除。



 
粵ICP備18138465號   © 2018-2025 CODEPRJ.COM