反爬篇 | 手把手教你处理 JS 逆向之字体反爬（下）

# 依赖
# OCR
pip3 install ddddocr

# 字体管理
pip3 install fontTools 

# 图片管理
pip3 install Pillow

def download_font(url, font_path):
    headers = {
        "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",
        "Accept-Encoding": "gzip, deflate, br",
        "Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8",
        "Cache-Control": "max-age=0",
        "Connection": "keep-alive",
        "Host": "www.maoyan.com",
        "Sec-Fetch-Dest": "document",
        "Sec-Fetch-Mode": "navigate",
        "Sec-Fetch-Site": "none",
        "Sec-Fetch-User": "?1",
        "Upgrade-Insecure-Requests": "1",
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36",
        "sec-ch-ua": "\"Not.A/Brand\";v=\"8\", \"Chromium\";v=\"114\", \"Google Chrome\";v=\"114\"",
        "sec-ch-ua-mobile": "?0",
        "sec-ch-ua-platform": "\"Windows\""
    }

    # 获取网页源码
    resp_pre = requests.get(url, headers=headers)
    resp = resp_pre.text

    # 解析出字体文件(woff格式)的下载地址
    font_file = re.findall(r's3plus\.meituan\.net\/v1\/mss_73a511b8f91f43d0bdae92584ea6330b\/font\/(\w+\.woff)', resp)[
        0]
    font_url = 'https://s3plus.meituan.net/v1/mss_73a511b8f91f43d0bdae92584ea6330b/font/' + font_file

font_headers = {
        'authority': 's3plus.meituan.net',
        'accept': '*/*',
        'accept-language': 'zh-CN,zh;q=0.9,en;q=0.8',
        'origin': 'https://www.**.com',
        'referer': 'https://www.**.com/',
        'sec-ch-ua': '"Not.A/Brand";v="8", "Chromium";v="114", "Google Chrome";v="114"',
        'sec-ch-ua-mobile': '?0',
        'sec-ch-ua-platform': '"Windows"',
        'sec-fetch-dest': 'font',
        'sec-fetch-mode': 'cors',
        'sec-fetch-site': 'cross-site',
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36',
    }

 # 下载字体文件到本地
 # 注意：这里下载字体必须使用特有的Header，不然下载的字体会受损
 font_content = requests.get(font_url, headers=font_headers)
 with open(f'./{font_file}', 'wb') as f:
     f.write(font_content.content)
     f.close()

from fontTools.ttLib.woff2 import decompress

...
# 将 woff文件转成 ttf 文件
decompress(font_file, font_path)

from PIL import ImageFont, Image, ImageDraw
from io import BytesIO
from fontTools.ttLib import TTFont
from fontTools.ttLib.woff2 import decompress
import ddddocr

def get_font_keymap(font_path):
    ...

    # 映射字典
    font_dict = {}

    # 解析字体文件中的编码对应关系
    for cmap_code, glyph_name in font.getBestCmap().items():
        # print(cmap_code,glyph_name)

        # 实例化一个图片对象（给定的模式和大小创建一个新图像） 白色
        img = Image.new('1', (img_size, img_size), 255)
        # img.show()

        # 绘制图片
        draw = ImageDraw.Draw(img)

        x, y = draw.textsize(chr(cmap_code), font=font_img)

        draw.text(((img_size - x) // 2, (img_size - y) // 2), txt, font=font_img, fill=0)
        bytes_io = BytesIO()
        img.save(bytes_io, format="PNG")

        # 使用OCR识别字体
        content= ocr.classification(bytes_io.getvalue())

        # 加入到键值对中
        font_dict[glyph_name] = content
    return font_dict

# 3、替换源码，将加密内容替换为明文
# .
for key in font_dict.keys():
    # print("key:", f'&#x{key[3:]};'.lower())
    # 去掉前面3个字符，将内容替换成对应的数字
    resp = resp.replace(f'&#x{key[3:]};'.lower(), font_dict[key])

import re
from lxml import etree
import os

# 使用lxml解析HTML
root = etree.HTML(resp)
elements = root.xpath('//span[@class="stonefont"]/text()')

for element in elements:
    print(element)