python爬虫字体加密的解决

2023-03-03 08:03:23 爬虫加密字体

解决步骤

获取到真正的源码
找到对应的字体库
进行解析操作.

获取到真正的源码

为什么用WEBdriver,因为requests拿不到真正的源码.

from selenium import webdriver
# --- 进行chrome的配置
options = webdriver.ChromeOptions()

prefs = {"profile.managed_default_content_settings.images": 2}  # 设置无图模式
options.add_experimental_option("prefs", prefs)
options.add_argument("service_args = ['–ignore-ssl-errors = true', '–ssl-protocol = TLSv1']")
options.binary_location = r'C:\Program Files\Google\Chrome\Application\chrome.exe'
# ---- chrome进行端口接管调用
options.add_argument('-incognito')

driver = webdriver.Chrome(options=options)
driver.set_page_load_timeout(5)
# --- 设置宽和高位置
driver.maximize_window()
# --- 拦截webdriver检测代码
driver.execute_cdp_cmd("Page.addScriptToEvaluateOnNewDocument",
                       {"source": """
                  Object.defineProperty(navigator, 'webdriver', {
                  get: () => undefined
                  })
                  """})

找到对应的字体库

在这里插入图片描述

这上面进行申明了告诉了我们这个是字体base64,然后就是那下来然后生成文件.

# 示例
import base64

# 省略了很长的...
b64_code = 'AAEAAAAKaiAAAwAgT1MvMla19RMAAACsAAAAYGNtYXAGQAPOAAABDAAAAa5nbHlmZrwdwAAAArwAAAakaGVhZBQx4JoAAAlgAAAANmhoZWEFswFxAAAJmAAAACRobXR4DVYBYgAACbwAAAAubG9jYQwQCnYAAAnsAAAAIm1heHAAFABOAAAKEAAAACBuYW1lUuodRwAACjAAAAGecG9zdDHgxUkAAAvQAAAAdAAEAgsBkAAFAAACMQLMAAAAjwKZAswAAAHrADMBCQAAAgAGAwAAAAAAAAAAAAEQAAAAAAAAAAAAAABQZkVkAMAAI4EEAyz/LABcAywA1AAAAAEAAAAAAxgAAAAAACAAAQAAAAQAAAADAAAAJAABAAAAAABcAAMAAQAAACQAAwAKAAABYgAEADgAAAAKAAgAAgACACMAKwAtAC///wAAACMAKgAtAC/e/9j/1//WAAEAAAAAAAAAAAAAAAABBgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAABAAAAAAAAAgMABAAFAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAMAAAAAABMAAAAAAAAAAUAAAAjAAAAIwAAAAEAAAAqAAAAKwAAAAIAAAAtAAAALQAAAAQAAAAvAAAALwAAAAUACID7AAiBBAAAAAYAAAACACIAAAEyAqoAAwAHAAA3ESERJzMRIyIBEO7MzAACqv1WIgJmAAAAAgAdAAACIALbABsAHwAAARUjByM3IwcjNyM1MzcjNTM3MwczNzMHMxUjByMzNyMB/4AmSCZrJ0knZnQjdoQkSSVrJkkmYnAitWwkbAEUR83Nzc1HuUjGxsbGSLm5AAAAAQAkAKQB3gI2ABEAABM3FyczBzcXBxcHJxcjNwcnNyQumSJzJZkun58umSRyIZguoAGXZ26mpGpmKClma6anbWYqAAABAEMAkwH6AkoACwAAARUjNSM1MzUzFTMVAUNKtrZKtwFKt7dJt7dJAAAAAAEAGgFCASQBrQADAAATNSEVGgEKAUJrawAAAAABAAD/gwEnAwoAAwAAFycTM0pK30h9AQOGAAAAAgAj//YCGgLmABMAJwAAARQOAiMiLgI1ND4CMzIeAgUUHgIzMj4CNTQuAiMiDgICGhw9X0NGYDwaGjxgR0JfPRz+qAgUJB0cJBUHBxQkHB0kFQgBb1WLYzY2Y4xVVYpiNTVii1VKc08qKk9zSklzTykpT3MAAAAAAQArAAACCgLfACEAADc1MzI+AjURDgMjIi4CNT4DPwEzERQeAjsBFWRUDRMNBhQiIB8PDRUQChAiJiwaSHIFCxUQUgA3Bg8aEwIBGCccDwoUHBEEDBIbEjX9mhAZEQg3AAAAAAEAJAAAAg4C5gArAAABFA4EDwEzMjY/ATMHITU3PgM1NCYjIgYVIi4CNTQ+AjMyHgIB9AsYKDtPM2fvHy0JCD0G/hyYLz0jDiomNCodMCMTHThUODpXPB4CPBgtMDZATjFhJCMf12qaMU5HRSg6NllYCxgnGxwyJhcYLD8AAAAAAQAd//YCDgLmAEQAABciLgI1ND4CMxQeAjMyPgI1NC4CKwE1MzI+AjU0JiMiDgIVIiY1ND4CMzIeAhUUDgIHHgMVFA4C+TpTNhkOGB8SEiEvHBktIxUVKDsnP0MhMSAQKyobIxMHQEUdOVQ4N1c+IRgqOSIfQtUiL01kChQiLRgTHhUKITEhEA4iOiweMSMUQBUoOCE4PxstOR4tLxsvJBQWKz4oIzouIgwFGSo/LD5VNBYAAgAOAAACKQLbABgAIwAAJRUUHgI7ARUhNTMyPgI9ASE1ATMRMxUlNDY3DgMPATMBvw0XHxEN/pkcEh4XDf7lASKPav8AAwQFFhkXBorUvz8YHQ8FNzcFDx0YPz4B3v4nQ/YtaDAMKiwoCeUAAQAp//YCBgLbADoAADcyPgI1NCYjIg4CBycTIRcjJy4DKwEUDgIPAT4DMzIeAhUUDgIjIi4CNTQ2MxQeAuwZLiIVSUMTIBsYCy8gAYQFOwgCBgsQDNUCAgMBCAgZHiIPPGBFJTBNXy85UDIXLSUMGIS+ECVAL0xLAwUHAxIBYrojCQ4KBgEQGyISXgMGBAMcNlI3Q1o3GBUiLRgkIxYsIxYAAAACAC7/9gIZAuYALAA8AAABIg4CBz4DMzIeAhUUDgIjIi4CNTQ+AjMyHgIVFA4CIzQuAgMiDgIHFB4CMzI2NTQmAUkeMSMVAwobIysaL0s2HR48WDs5XUMlJEhuSjJFKxMNHS4iBg8bNw4fHBgGEh4pFygtMgKpJEVkQQcNCwcdN04yN1tBJCpWg1lVk20/EyAoFhAdFg0XLyYY/tkIDhIJSWpEIFBZU0wAAAAAAQAtAAACGwLbAAsAADcBISIGDwEjNyEVAakBEf7yHBwDBj4FAen+5QACbBsZNNcy/VcAAAMAH//2Ah4C5gAlADkATQAANzQ+AjcuATU0PgIzMh4CFRQOAgceAxUUDgIjIi4CFzI+AjU0LgInDgMVFB4CEzQuAiMiDgIVFB4CFz4DHxUoOCE9QRg4W0I2UjcbEyQzIC5BKBMkQ2E+QF4+Hf4aKx4QESU4KBEeFQ0RHit6DBgkFxUhFgsOHCkbExsSCLshNSslESNaPCRDNCAbMEInHi8nIRAXLTI2HzFLNBwfNUhiEyIvHBkpIyISCx0jLBseMiMUAgQWKyEUER8qGBsoIBkNCxkgKAAAAAIAJP/2Ag8C5gAoADYAABciLgI1NDY3HgMzMjY3DgMjIi4CNTQ+AjMyHgIVFA4CAzI2NzQuAiMiBhUUFukvQCgRGBoHFR4nGkVKBQwdJS0aLEo1HiA9Vzc3XkUmIUdvHyU1DxEcKBgsMDAKFCAqFhYfBRcoHRGVkw8ZEwobNk80N1tCJChUglpVlG9AAW4lH0JePB1WV0dJAAAAAAEAAAABAACt4Ie1Xw889QALBAAAAAAA2XTOiAAAAADZdM6IAAD/gwIpAwoAAAAIAAIAAAAAAAAAAQAAAyz/LABcAj0AAAAAAikAAQAAAAAAAAAAAAAAAAAAAAcBdgAiAj0AHQICACQCPQBDAT4AGgEnAAACPQAjACsAJAAdAA4AKQAuAC0AHwAkAAAAAAAUAEQAZgB8AIoAmADUAQYBRgGgAdYCKAJ+ApgDBANSAAAAAQAAABAATgADAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAwAlgABAAAAAAABAA0AAAABAAAAAAACAAYADQABAAAAAAADAA0AEwABAAAAAAAEAA0AIAABAAAAAAAFAB4ALQABAAAAAAAGAA0ASwADAAEECQABABoAWAADAAEECQACAAwAcgADAAEECQADABoAfgADAAEECQAEABoAmAADAAEECQAFADwAsgADAAEECQAGABoA7kxlZVRyZWVzaGFkb3dNZWRpdW1MZWVUcmVlc2hhZG93TGVlVHJlZXNoYWRvd1ZlcnNpb24gMS4wOyBGb250RWRpdG9yICh2MS4wKUxlZVRyZWVzaGFkb3cATABlAGUAVAByAGUAZQBzAGgAYQBkAG8AdwBNAGUAZabpAHUAbQBMAGUAZQBUAHIAZQBlAHMAaABhAGQAbwB3AEwAZQBlAFQAcgBlAGUAcwBoAGEAZABvAHcAVgBlAHIAcwBpAG8AbgAgADEALgAwADsAIABGAG8AbgB0AEUAZABpAHQAbwByACAAKAB2ADEALgAwACkATABlAGUAVAByAGUAZQBzAGgAYQBkAG8AdwAAAAIAAAAAAAAAMgAAAAAAAAAAAAAAAAAAAAAAAAAAABAAEAAAAAYADQAOABAAEgECAQMBBAEFAQYBBwEIAQkBCgELBHplcm8Db25lA3R3bwV0aHJlZQRmb3VyBGZpdmUDc2l4BXNldmVuBWVpZ2h0BG5pbmU='

with open('font.ttf', 'wb') as f:
    f.write(base64.decodebytes(b64_code.encode()))


from fontTools.ttLib import TTFont  # 导包

font = TTFont('font.ttf')
font.saveXML('font.xml')

# 简单封装下
import base64
def w_tff(one_html):
    res_tff = re.findall(r';base64,(.*?)"', one_html, re.S)
    if res_tff and len(res_tff) == 1:
        new_res_ttf = res_tff[0]
        with open('123_new_ttf.ttf', 'wb') as f:
            f.write(base64.decodebytes(new_res_ttf.encode()))

读取文件找到里面的对应关系,就是你这个数字的格式是存储在.ttf文件里的.

from fontTools.ttLib import TTFont
def get_num_phone(es_str: str):
    # 加载字体生成映射关系
    path = '123_new_ttf.ttf'
    font = TTFont(path)

    # font.saveXML('font.xml')   # 生成xml文件
    # 得到映射关系
    bestcmap = font.getBestCmap()

    ss = {}
    for key, value in bestcmap.items():
        keys = hex(key).replace('0x', '').replace("&#x", "")  # 10进制转16进制
        if value == "zero":
            value = 0
        elif value == "one":
            value = 1
        elif value == "one":
            value = 1
        elif value == "two":
            value = 2
        elif value == "three":
            value = 3
        elif value == "four":
            value = 4
        elif value == "five":
            value = 5
        elif value == "six":
            value = 6
        elif value == "seven":
            value = 7
        elif value == "eight":
            value = 8
        elif value == "nine":
            value = 9
        elif value == "hyphen":
            value = "-"
        ss.update({
            keys: value
        })

    need_re = es_str
    list_phone = ""
    try:
        for item in need_re.split(";"):
            if item:
                new_item = item.replace("&#x", "")
                list_phone += "".join(str(ss[new_item]))
        if not list_phone or len(list_phone) < 2:
            return None
        return list_phone
    except Exception as e:
        return None

<cmap>
    <tableVersion version="0"/>
    <cmap_fORMat_4 platformID="0" platEncID="3" language="0">
      <map code="0x23" name="numbersign"/><!-- NUMBER SIGN -->
      <map code="0x2a" name="asterisk"/><!-- ASTERISK -->
      <map code="0x2b" name="plus"/><!-- PLUS SIGN -->
      <map code="0x2d" name="hyphen"/><!-- HYPHEN-MINUS -->
      <map code="0x2f" name="slash"/><!-- SOLIDUS -->
    </cmap_format_4>
    <cmap_format_0 platformID="1" platEncID="0" language="0">
      <map code="0x23" name="numbersign"/>
      <map code="0x2a" name="asterisk"/>
      <map code="0x2b" name="plus"/>
      <map code="0x2d" name="hyphen"/>
      <map code="0x2f" name="slash"/>
    </cmap_format_0>
    <cmap_format_4 platformID="3" platEncID="1" language="0">
      <map code="0x23" name="numbersign"/><!-- NUMBER SIGN -->
      <map code="0x2a" name="asterisk"/><!-- ASTERISK -->
      <map code="0x2b" name="plus"/><!-- PLUS SIGN -->
      <map code="0x2d" name="hyphen"/><!-- HYPHEN-MINUS -->
      <map code="0x2f" name="slash"/><!-- SOLIDUS -->
    </cmap_format_4>
    <cmap_format_12 platformID="3" platEncID="10" format="12" reserved="0" length="76" language="0" nGroups="5">
      <map code="0x23" name="numbersign"/><!-- NUMBER SIGN -->
      <map code="0x2a" name="asterisk"/><!-- ASTERISK -->
      <map code="0x2b" name="plus"/><!-- PLUS SIGN -->
      <map code="0x2d" name="hyphen"/><!-- HYPHEN-MINUS -->
      <map code="0x2f" name="slash"/><!-- SOLIDUS -->
      <map code="0x880fb" name="zero"/><!-- ???? -->
      <map code="0x880fc" name="one"/><!-- ???? -->
      <map code="0x880fd" name="two"/><!-- ???? -->
      <map code="0x880fe" name="three"/><!-- ???? -->
      <map code="0x880ff" name="four"/><!-- ???? -->
      <map code="0x88100" name="five"/><!-- ???? -->
      <map code="0x88101" name="six"/><!-- ???? -->
      <map code="0x88102" name="seven"/><!-- ???? -->
      <map code="0x88103" name="eight"/><!-- ???? -->
      <map code="0x88104" name="nine"/><!-- ???? -->
    </cmap_format_12>
  </cmap>

读取ttf文件,(再生成xml文件,第一次寻找映射关系是需要做的)

font.getBestCmap() 获取映射关系表
我们观察 xml文件的cmap段进行研究 ,可以看到我们明确需要的结果
keys = hex(key).replace('0x', '').replace("&#x", "") 10进制转16进制 ,会得到映射关系表 {'23': 'numbersign', '2a': 'asterisk', '2b': 'plus', '2d': '-', '2f': 'slash', '8826e': 0, '8826f': 1, '88270': 2, '88271': 3, '88272': 4, '88273': 5, '88274': 6, '88275': 7, '88276': 8, '88277': 9}
和从页面上那些来的结果进行逐个匹配调整就行了.

注意的点

webdriver拿下来的页面源码有可能有点问题,所以我用了 soup_text = bs4.BeautifulSoup(driver.page_source, 'lxml').text 的方法来处理源代码 (import bs4)

其他的就是一些小细节上的问题了.基本的思路就是这样的.

到此这篇关于python爬虫字体加密的解决的文章就介绍到这了,更多相关python爬虫字体加密内容请搜索以前的文章或继续浏览下面的相关文章希望大家以后多多支持！

相关文章

python爬虫字体加密的解决

目录

解决步骤

获取到真正的源码

注意的点