貓眼的數字解密

話很少說，直接乾貨走起：

 

 

 看到了嗎？字體加密了。那就找。。定位到加密字體的地方，而後看右邊的styles,你是否是看到了與字體相關的名字—font-family，就是他，複製他而後源碼裏面全局搜索，你會看到以下東西：

 woff？就是這個字體文件。正則拿下來，接下來是正題

# 獲取源碼裏面的字體加密源碼
base_str = re.findall(r"base64,(.*?)\)",response.text)[0]

將base64編碼的字體字符串解碼成爲二進制格式，寫成.woff文件，再經過BytesIO把一個二進制內存塊當成一個文件來操做

def make_font_file(base64_string: str):
    #將base64編碼的字體字符串解碼成爲二進制格式
    bin_data = base64.decodebytes(base64_string.encode())
    with open('testotf.woff','wb') as f:
        f.write(bin_data)
    return bin_data
def convert_font_to_xml(bin_data):
    #BytesIO把一個二進制內存塊當成一個文件來操做
    font = TTFont(BytesIO(bin_data))
    #將解碼字體保存爲xml
    font.saveXML('test1.xml')

再用畫筆把他畫出來，順便使用pytesseract庫把他識別出來

def draw(path):
    #接下來就是畫字體了
    #建立一張空的畫板，大小爲80*30，默認填充爲白色
    im = Image.new('RGB',(90,30),(255,255,255))
    #獲取繪製的上下文環境（繪製的起始地址）
    dr = ImageDraw.Draw(im)
    #建立要繪製的字體
    font = ImageFont.truetype(BytesIO(make_font_file(base_str)),18)
    #開始繪製（10,5）是起始繪製座標，fill指明字體的填充色爲黑色
    dr.text((10,5),text,font=font,fill="#000000")
    im.save('hh.jpg')
    result = pytesseract.image_to_string(path).replace(' ','.')
    return result

這樣就能夠獲得解碼後的數字了。。

不過畢竟識別確定不是百分之百能成功的。另外還有一種能夠徹底實現，可是他的對應關係還沒找到，搞了一半，半成品（我發現這個能夠https://www.jianshu.com/p/5aa978e9823d）不過又驗證了一下，發現他的字體庫是在變化的，因此說這個好像不能夠用了。這個是字體解碼對應的軟件下載地址http://www.mydown.com/soft/359/509448859.shtml

base_str1 = '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'
baseFont = TTFont(BytesIO(make_font_file(base_str)))
def decode_font_advance(font_str):
    match_font = TTFont(BytesIO(make_font_file(font_str)))
    numDic = {}
    uniList = match_font['cmap'].tables[0].ttFont.getGlyphOrder()[1:]
    baseNumList = ['.', '4', '7', '8', '9', '0', '6', '2', '1', '5', '3']
    baseUnicode = ['x','uniEBDD','uniECB5','uniEBC9','uniF0D3','uniECCE','uniEE54','uniE90C','uniE027','uniE4BF','uniE791']
    for i in range(11):
        #找到相應字形對應繪製圖元的對象
        matchGlyph = match_font['glyf'][baseUnicode[i]]
        for j in range(11):
            baseGlyph = baseFont['glyf'][baseUnicode[j]]
            #若是相應繪製圖元相等，認爲兩個字形相等
            if matchGlyph == baseGlyph:
                #從已知對應關係列表中查出對應文字
                numDic[uniList[i]] = baseNumList[j]
                print(numDic[uniList[i]],baseNumList[j])
                break
    result = ''
    j = 0  # 標記小數點位置
    for i in range(len(text)):
        if text[i] != '.':
            num = 'uni' + text[i].encode('unicode-escape').decode()[2:].upper()
            if num in numDic:
                result += numDic[num]
        else:
            j = i
    result = result[0:j] + '.' + result[j:]
    return result

 

 這一塊的對應關係不對，因此這個暫時能夠不用！！

到這裏，確定都是想要源碼的，這裏直接貼上

 

import re
import base64
import requests
import lxml.html
from io import  BytesIO
from fontTools.ttLib import TTFont
from PIL import Image,ImageDraw,ImageFont

from pytesseract import pytesseract

#fontTools 對字體進行分析解析及建立
#PIL(pillow)圖片處理庫
#base64 對base64字符串進行編碼和解碼
#pytesseract python 提供的一個操做tesseract庫的封裝
#tesseract 進行文字OCR（將圖片的文字轉換爲文本）識別的機器學習庫  tts（將語音轉換爲文本或文本轉換爲語音）
#字體文件本質是編碼到繪製方式的一種映射方式，同時存儲了字體的繪製矩陣

#動態獲取base_str
headers={"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64; rv:64.0) Gecko/20100101 Firefox/64.0s",}
url = 'http://piaofang.maoyan.com/?ver=normal&isid_key='這個本身登錄以後會有的，本身加上
# url = 'http://piaofang.maoyan.com/?ver=normal'

response = requests.get(url=url,headers=headers)
tree = lxml.html.fromstring(response.text)
#獲取加密字體列表裏面的數字是能夠本身選擇，一次只能走一個
text = tree.xpath('//div[@id="ticket_tbody"]/ul[@class="canTouch"]/li/b/i/text()')[0].strip()
# 獲取源碼裏面的字體加密源碼
base_str = re.findall(r"base64,(.*?)\)",response.text)[0]

def make_font_file(base64_string: str):
    #將base64編碼的字體字符串解碼成爲二進制格式
    bin_data = base64.decodebytes(base64_string.encode())
    with open('testotf.woff','wb') as f:
        f.write(bin_data)
    return bin_data
def convert_font_to_xml(bin_data):
    #BytesIO把一個二進制內存塊當成一個文件來操做
    font = TTFont(BytesIO(bin_data))
    #將解碼字體保存爲xml
    font.saveXML('test1.xml')
#先把拿到的字體源碼生成xml格式的，你能夠進去看一下里面是什麼


def draw(path):
    #接下來就是畫字體了
    #建立一張空的畫板，大小爲80*30，默認填充爲白色
    im = Image.new('RGB',(90,30),(255,255,255))
    #獲取繪製的上下文環境（繪製的起始地址）
    dr = ImageDraw.Draw(im)
    #建立要繪製的字體
    font = ImageFont.truetype(BytesIO(make_font_file(base_str)),18)
    #開始繪製（10,5）是起始繪製座標，fill指明字體的填充色爲黑色
    dr.text((10,5),text,font=font,fill="#000000")
    im.save('hh.jpg')
    result = pytesseract.image_to_string(path).replace(' ','.')
    return result
if __name__ == '__main__':
    convert_font_to_xml(make_font_file(base_str))
    print(draw('hh.jpg'))

 

我知道你還缺乏pytesseract 庫，https://digi.bib.uni-mannheim.de/tesseract/直接下載吧，記得下載完，修改一下pytesseract.py這個文件下的tesseract_cmd，這個後面跟你的路徑