Bump requests from 2.21.0 to 2.31.0 in /bilibili

.gitignore

@@ -99,3 +99,6 @@ ENV/
 
 # mypy
 .mypy_cache/
+bilibili/log
+.DS_Store
+bilibili/log.err

AWS/Amazon_Utils.py

@@ -0,0 +1,193 @@
+# -*- coding:UTF-8 -*-
+import xlrd
+import xlwt
+import os
+import re
+import requests
+def is_bash():
+    '''判断使用平台'''
+    if platform.system().lower() == "windows":
+        return 0
+    if platform.system().lower() == 'darwin' or platform.system().lower() == 'linux':
+        return 1
+def is_TTD(f):
+    '''是否被Amazon屏蔽请求变狗'''
+    temp = f
+    if(re.findall("(_TTD_\.jpg)", f)):
+        return 1
+    else:
+        return 0
+def retry(func):
+    '''装饰器：try最多5次'''
+    def wrap(*args):
+        i = 0
+        r  = None
+        while i<5:
+            try:
+                r = func(*args)
+                if r:
+                   i = 5 
+            except Exception as e:
+                i+=1
+        return r
+    return wrap
+
+def excel_bulit(workbook, asin):
+    '''Bulit a excel.构建Excel'''
+    table= workbook.add_sheet("{}".format(asin),cell_overwrite_ok=True)
+    style = xlwt.XFStyle()#设置样式
+    font = xlwt.Font()#设置字体
+    font.name = 'SimSun' # 指定“宋体”
+    style.font = font
+    alignment=xlwt.Alignment()#设置对齐
+    alignment.horz=xlwt.Alignment.HORZ_CENTER#单元格字符水平居中
+    # 格式: HORZ_GENERAL, HORZ_LEFT, HORZ_CENTER, HORZ_RIGHT, HORZ_FILLED, HORZ_JUSTIFIED, HORZ_CENTER_ACROSS_SEL, HORZ_DISTRIBUTED
+    alignment.vert=xlwt.Alignment.VERT_CENTER#单元格字符垂直居中
+    #格式: VERT_TOP, VERT_CENTER, VERT_BOTTOM, VERT_JUSTIFIED, VERT_DISTRIBUTED
+    style.alignment=alignment#添加至样式
+    return table
+
+def Get_ASINlists(fn):
+    '''从表格里获取ASINURL'''
+    data=xlrd.open_workbook(fn) # 打开工作薄
+    sheets=data.sheets()
+    z={}
+    p=0
+    for sheet in sheets:
+        p+=1
+        z[p]=sheet.name
+        print(p,z[p])
+    try:
+        sheet_index=int(input("plz input index in the serial number(default 1):\n"))
+        if sheet_index in range(1,len(sheets)+1):
+            t=sheet_index
+        else:
+            print('The digital is wrong,plz input a correct number')
+    except Exception as e:
+        print(str(e))
+        t=1
+    table=data.sheet_by_index(t-1) # 读取指定sheet
+    cols=table.ncols
+    rows=table.nrows
+    print("{0}'s rows ,cols are {1},{2}".format(z[t],rows,cols))
+    first_sheet=table.row_values(0)
+    try:
+        url_index=first_sheet.index('ASIN')#返回第一行URL的列数
+    except Exception as e:
+        print(e)
+        return []
+    ASINs=table.col_values(url_index) # 读取指定列（该列含有URL）
+    ASINs.pop(0)
+    return ASINs
+def Get_Exceldata(fn, colname):
+    '''从表格里获取任意列数组'''
+    if not os.path.exists(fn):
+        print("Doesn't exist: {}".format(os.path.abspath(fn)))
+        return None
+    data=xlrd.open_workbook(fn) # 打开工作薄
+    sheets=data.sheets()
+    z={}
+    p=0
+    for sheet in sheets:
+        p+=1
+        z[p]=sheet.name
+        print(p,z[p])
+    try:
+        sheet_index=int(input("plz input index in the serial number(default 1):\n"))
+        if sheet_index in range(1,len(sheets)+1):
+            t=sheet_index
+        else:
+            print('The digital is wrong,plz input a correct number')
+    except Exception as e:
+        print(str(e))
+        t=1
+    table=data.sheet_by_index(t-1) # 读取指定sheet
+    cols=table.ncols
+    rows=table.nrows
+    print("{0}'s rows ,cols are {1},{2}".format(z[t],rows,cols))
+    first_sheet=table.row_values(0)
+    try:
+        url_index=first_sheet.index(colname)#返回第一行URL的列数
+    except Exception as e:
+        print(e)
+        return []
+    ASINs=table.col_values(url_index) # 读取指定列（该列含有URL）
+    ASINs.pop(0)#去掉表头
+    return ASINs
+
+def File_path_choice():
+    '''选择文件夹中的文件，返回所选文件路径'''
+    t='./stainless steel toilet brush holder.xlsx'#默认工作簿地址
+    try:
+        file_path='.'
+        print('当前路径{0}文件夹中的文件和文件夹如下：'.format(os.path.abspath(file_path)))
+        file_names=os.listdir(file_path)#列出下载文件夹中的文件名
+        for i in range(len(file_names)):
+            print(i+1,file_names[i])
+        file_num=int(raw_input("Default workbook is 1,plz input a number of serial number(default {0}):\nOr Enter a number more than the last option you could input a url of file\n ".format(t)))#默认文件名是t,或者输入比最后选项大的数
+        if file_num in range(1,len(file_names)+1):
+            file_path=file_path+'/'+file_names[file_num-1]
+        if file_num>=len(file_names)+1:
+            file_path=str(raw_input("plz input a fileurl (like:D:\\Documents\\Downloads\1.xlsx or /Users/\{name\}/Projects/1.xls\n"))
+            f=os.path.exists(file_path)
+            while f==False:
+                file_path=str(raw_input("Your file is not exsits,plz input a fileurl:\n"))
+                f=os.path.exists(file_path)
+    except Exception as e:
+        print(str(e))
+        file_path=t
+    return file_path
+
+def is_Captcha(f, host, asin, session, headers):
+    '''Amazon验证码'''
+    url = re.findall("(https://images-na.ssl-images-amazon.com/captcha.*?jpg)", f)
+    i = 0
+    while url:
+        captcha = AmazonCaptcha.fromlink(url[0])
+        text = captcha.solve()
+#        with open('./t.html', 'w') as f:
+#            f.write(r)
+#            f.close()
+        validateCaptcha_url = host+"/errors/validateCaptcha"
+        amzn = re.findall("name=\"amzn\" value=\"(.*?)\"", f)[0]
+        amzn_r = re.findall("name=\"amzn-r\" value=\"(.*?)\"", f)[0]
+        params = {
+            "amzn": amzn,
+            "amzn-r": html.unescape(amzn_r),
+            "field-keywords": text
+        }
+        validateCaptcha_url = validateCaptcha_url+"?"+ urllib.parse.urlencode(params)
+        print(validateCaptcha_url)
+        r = session.get(validateCaptcha_url, headers = headers, timeout = 5)#Amazon验证请求
+        u = host+asin
+        r = session.get(u, headers=headers, timeout = 5)
+        f = r.text
+        print(url)
+        url = re.findall("(https://images-na.ssl-images-amazon.com/captcha.*?jpg)", f)
+        i += 1
+        if i == 5:
+            url = []
+    return f, session
+
+def requests_asin(host, asin):
+    '''Get the content of Amazon listing web page.获取listing网页内容'''
+    headers={
+        'Connection':'keep-alive',
+        'sec-ch-ua':'"Google Chrome";v="111", "Not(A:Brand";v="8", "Chromium";v="111"',
+        'sec-ch-ua-mobile':'?0',
+        'sec-ch-ua-platform':'"macOS"',
+        'Upgrade-Insecure-Requests':'1',
+        'User-Agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/111.0.0.0 Safari/537.36',
+        'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
+        'Sec-Fetch-Site':'none',
+        'Sec-Fetch-Mode':'navigate',
+        'Sec-Fetch-User':'?1',
+        'Sec-Fetch-Dest':'document',
+        'Accept-Encoding':'gzip, deflate, br',
+        'Accept-Language':'en-US,en;q=0.9'
+        }#浏览器头部
+    #proxies={'HTTP': 'HTTP://127.0.0.1:1081', 'HTTPS': 'HTTPS://127.0.0.1:1081'}#免费代理IP
+    session=requests.Session()
+    url = host+'/dp/'+asin
+    r = session.get(url, headers=headers, timeout = 5)
+    return is_Captcha(r.text, host, asin, session, headers)

AWS/Amazozn_email.py

@@ -0,0 +1,149 @@
+# -*- conding:UTF-8 -*-
+# Author:Toryun
+# Python version:2.7.13
+# Date:18/3/25
+# Function:Create a style Excel in special situation生成指定表格,写入随机Email和密码
+#Amazom CAPTCHA IMG API  https://www.amazon.com/ap/captcha?appAction=REGISTER&captchaObfuscationLevel=ape:aGFyZA==&captchaType=image
+import random
+import requests
+import xlwt
+import xlrd
+import datetime,time
+import mechanize
+import os
+import cookielib
+import sys
+from PIL import Image
+import re
+#---------------------------------------------------------------------------------
+def excel_bulit():
+    #Bulit a excel,Generate a  account  of Amazon 构建Excel，生成亚马逊账号
+    workbook = xlwt.Workbook(encoding = 'utf-8')
+    table= workbook.add_sheet("data",cell_overwrite_ok=True)
+    style = xlwt.XFStyle()#设置样式
+    font = xlwt.Font()#设置字体
+    font.name = 'SimSun' # 指定“宋体”
+    style.font = font
+    alignment=xlwt.Alignment()#设置对齐
+    alignment.horz=xlwt.Alignment.HORZ_CENTER#单元格字符水平居中
+    # 格式: HORZ_GENERAL, HORZ_LEFT, HORZ_CENTER, HORZ_RIGHT, HORZ_FILLED, HORZ_JUSTIFIED, HORZ_CENTER_ACROSS_SEL, HORZ_DISTRIBUTED
+    alignment.vert=xlwt.Alignment.VERT_CENTER#单元格字符垂直居中
+    #格式: VERT_TOP, VERT_CENTER, VERT_BOTTOM, VERT_JUSTIFIED, VERT_DISTRIBUTED
+    style.alignment=alignment#添加至样式
+
+    for i in range(0,100):
+        t='0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ'
+        t1=''.join(random.sample(t,8))
+        b1=''.join(random.sample(t,8))
+        mail=t1+'@gmail.com'
+        table.write(i,0,mail,style)
+        table.write(i,1,b1,style)
+    file_save='C:\\Users\\Administrator\\Desktop\email.xls'    
+    workbook.save(file_save)
+
+#---------------------------------------------------------------------------------
+#Reading account accounts and passwords
+#读取账户账号和密码
+def read_excel(i):
+    '''Read account and password from workbook读取工作簿中的账号密码'''
+    workbook=xlrd.open_workbook('C:\\Users\\Administrator\\Desktop\email.xls')
+    table=workbook.sheet_by_index(0)
+    account=table.col_values(0)
+    password=table.col_values(1)
+    a=account[i]
+    p=password[i]
+    return a,p
+#---------------------------------------------------------------------------------
+#Register Amazon（Using mechanize library to simulate browser registration）
+#注册亚马逊(使用mechanize库模拟浏览器注册）
+def register(name,account,password,i):
+    '''Using the mechanize lib simulation browser to large quantity register Amazon accounts使用mechanize模拟浏览器批量注册亚马逊账号'''
+    url='https://www.amazon.com/ap/register?openid.pape.max_auth_age=0&openid.identity=http%3A%2F%2Fspecs.openid.net%2Fauth%2F2.0%2Fidentifier_select&pageId=usflex&ignoreAuthState=1&openid.return_to=https%3A%2F%2Fwww.amazon.com%2F%3Fref_%3Dnav_ya_signin&prevRID=3CBEZNC1DVKVH5BS3CQT&openid.assoc_handle=usflex&openid.mode=checkid_setup&openid.ns.pape=http%3A%2F%2Fspecs.openid.net%2Fextensions%2Fpape%2F1.0&prepopulatedLoginId=&failedSignInCount=0&openid.claimed_id=http%3A%2F%2Fspecs.openid.net%2Fauth%2F2.0%2Fidentifier_select&openid.ns=http%3A%2F%2Fspecs.openid.net%2Fauth%2F2.0'
+    br = mechanize.Browser()
+    br.set_handle_equiv(True)#handle HTTP-EQUIV headers (HTTP headers embedded in HTML).
+    br.set_handle_redirect(True)
+    br.set_handle_referer(True)#add Referer (sic) header
+    br.set_handle_robots(False)# Ignore robots.txt.  Do not do this without thought and consideration.
+    br.set_handle_gzip(False)
+    br.set_handle_refresh(mechanize._http.HTTPRefreshProcessor(), max_time=1)
+    br.addheaders = [('User-agent', 'Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:59.0) Gecko/20100101 Firefox/59.0')]
+    proxies={"HTTPS": "HTTPS://122.242.96.30:808"}#proxy代理
+    br.set_proxies(proxies)
+    for tries in range(10):#解决100610错误问题（代理连接问题）
+        try:
+            br.open(url)
+        except:
+            if tries<=10:
+                continue
+            else:
+                break
+    br.select_form(nr=0)
+    br.form['customerName']=name
+    br.form['email']=account
+    br.form['password']=password
+    br.form['passwordCheck']=password
+    br.submit()
+    response=str(br.response().read())
+    try:#如果需要验证进行以下操作
+        img_url=re.findall(r'<img alt="Visual CAPTCHA image, continue down for an audio option." src="(.*?)" data-refresh-url',response)#读取验证码图片
+        headers={"Host":	
+        "opfcaptcha-prod.s3.amazonaws.com",
+        "Referer":
+        "https://www.amazon.com/ap/register",
+        "User-Agent":
+        "Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:59.0) Gecko/20100101 Firefox/59.0",
+        "Accept":
+        "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
+        "Accept-Language":
+        "zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2",
+        "Accept-Encoding":	
+        "gzip, deflate, br",
+        "Connection":
+        "keep-alive",
+        "Upgrade-Insecure-Requests":"1"
+        }
+        if img_url[0]:
+            img_url0=img_url[0].replace("&amp;","&",2)
+            print 'Need captcha'
+        r=requests.get(img_url0,headers=headers,proxies=proxies)#下载验证码图片
+        print r.status_code
+        if r.status_code==200:
+            _img_0="d:jpg/"+str(i)+".jpg"#存储验证码图片路径
+            with open(_img_0,"wb") as _img_1:
+                _img_1.write(r.content)
+                _img_1.close()
+            img = Image.open(_img_0)
+            img.show()
+            guess=raw_input('Plz input Type characters you see:\n')
+            command = 'taskkill /F /IM dllhost.exe'#强制终止指定进程名命令
+            os.system(command)
+            br.select_form(nr=0) 
+            br.form['password']=password
+            br.form['passwordCheck']=password
+            br.form['guess']=guess
+            br.submit()  
+    except Exception,e:
+        print str(e)
+        pass
+#---------------------------------------------------------------------------------   
+#Simulate download progress of Lniux 
+#模拟Lniux下载进度条
+def  progress(i):
+    r='\r%s>%d%%' % ('#' * i, i,)
+    sys.stdout.write(r)
+    sys.stdout.flush()#Refresh progress刷新进度条
+def rate_progress(i):
+    sys.stdout.write('\r%2d%%')
+    sys.stdout.flush()
+
+if __name__=='__main__':
+    t1=datetime.datetime.now()
+    excel_bulit()
+    print 'email is built,now register amazon account\n完成进度:\n'.decode('utf-8')
+    for i in range(0,100):
+        a,p=read_excel(i)
+        register(name=p,account=a,password=p,i=i)
+        time.sleep(random.randint(0,6))#随机休息0到6秒
+        progress(i)     
+    t2=datetime.datetime.now()
+    print "\nThe cost time is {0}.\nThe workbook is saved in {1}".format(t2-t1,'C:\\Users\\Administrator\\Desktop\email.xls' )