2019年末逆向复习系列之从猫眼字体反爬分析谈谈字体反爬的前世今生

python -m fonts.xxxx

@font-face {
 font-family: <identifier>;
 src: <fontsrc> [, <fontsrc>]*; <font>;
  }

“替换数据”=“$#x{woff文件中被替换数据的编码}”

from pathlib import Path
from fontTools.ttLib import TTFont
woff_path = Path(__file__).absolute().parent/"base64 (1).woff"
font = TTFont(woff_path)
font_names = font.getGlyphOrder()
font_str = [
    "8", "验", "杨", "女", "3", "届", "7", "男", "高", "赵", "6", "2", "下", "以", "技", "黄", "周",
    "4", "经", "专", "硕", "刘", "吴", "陈", "士", "E", "5", "中", "博", "1", "科", "大", "9", "本",
     "王", "B", "无", "李", "应", "生", "校", "A", "0", "张","M"
]
print(dict(zip(font_names[2:],font_str)))

{'uniE032': '8', 'uniE200': '验', 'uniE267': '杨', 'uniE2DF': '女', 'uniE34E': '3', 'uniE39C': '届',
'uniE42A': '7', 'uniE481': '男', 'uniE51F': '高', 'uniE555': '赵
', 'uniE595': '6', 'uniE608': '2', 'uniE6CD': '下', 'uniE72D': '以', 'uniE7C1': '技', 'uniE7C6': '黄',
'uniE7D3': '周', 'uniE841': '4', 'uniE84B': '经', 'uniE8A4': '专', 'uniE8E6': '硕', 'uniE8F4': '刘',
'uniE906': '吴', 'uniE9CF': '陈', 'uniEA8F': '士', 'uniEB2C': 'E', 'uniEBBA': '5', 'uniEBE2': '中', 'uniED0E': '博',
 'uniEF3E': '1', 'uniF003': '科', 'uniF012': '大', 'uniF01A': '9', 'uniF02F': '本',
'uniF0D7': '王', 'uniF160': 'B', 'uniF180': '无', 'uniF205': '李', 'uniF2A0': '应', 'uniF3B5': '生', 'uniF501': '校',
 'uniF6E9': 'A', 'uniF71C': '0', 'uniF76F': '张', 'uniF877': 'M'}

from pathlib import Path
from fontTools.ttLib import TTFont
font1_path = Path(__file__).absolute().parent/"font_1.xml"
font2_path = Path(__file__).absolute().parent/"font_2.xml"
woff1_path = Path(__file__).absolute().parent/"base64 (1).woff"
woff2_path = Path(__file__).absolute().parent/"base64 (2).woff"
font_1 = TTFont(woff1_path)
font_2 = TTFont(woff2_path)
font_1.saveXML(font1_path)
font_2.saveXML(font2_path)

from pathlib import Path
from fontTools.ttLib import TTFont
woff1_path = Path(__file__).absolute().parent/"base64 (1).woff"
woff2_path = Path(__file__).absolute().parent/"base64 (2).woff"
font_1 = TTFont(woff1_path)
font_2 = TTFont(woff2_path)
font_old_order = font_1.getGlyphOrder()[2:]
font_new_order = font_2.getGlyphOrder()[2:]


def get_font_flags(font_glyphorder, font_ttf):
    f = {}
    for i in font_glyphorder:
        flags = font_ttf['glyf'][i]
        if "flags" in flags.__dict__:
            f[tuple(list(flags.flags))] = i
    return f


def comp(arr1, arr2):
    if len(arr1) != len(arr2):
        return 0
    for i in range(len(arr2)):
        if arr1[i] != arr2[i]:
            return 0
    return 1


def get_old_new_mapping():
    old, new = get_font_flags(font_glyphorder=font_old_order, font_ttf=font_1), get_font_flags(
        font_glyphorder=font_new_order, font_ttf=font_2)
    result_dict = {}
    for key1, value1 in old.items():
        for key2, value2 in new.items():
            if comp(key1, key2):
                result_dict[value1] = value2
    return result_dict


print(get_old_new_mapping())

{'uniE032': 'uniF889', 'uniE595': 'uniEB52', 'uniF01A': 'uniF07A', 'uniF71C': 'uniEBDE'}

python -m maoyan.xxxx

def get_font_content() -> str:
    response = requests.get(
        url=_brand_url,
        headers=_headers
    )
    woff_url = re.findall(r"url\('(.*?\.woff)'\)", response.text)[0]
    font_url = f"http:{woff_url}"
    return requests.get(font_url).content


def save_font() -> None:
    for i in range(5):
        font_content = get_font_content()
        with open(f'./fonts/{i+1}.woff', 'wb') as f:
            f.write(font_content)


def get_coor_info(font, cli):
    glyf_order = font.getGlyphOrder()[2:]
    info = list()
    for i, g in enumerate(glyf_order):
        coors = font['glyf'][g].coordinates
        coors = [_ for c in coors for _ in c]
        coors.insert(0, cli[i])
        info.append(coors)
    return info

def get_font_data() -> List[List[List[int]]]:
    font_1 = TTFont('./fonts/1.woff')
    cli_1 = [6, 7, 4, 9, 1, 2, 5, 0, 3, 8]
    coor_info_1 = get_coor_info(font_1, cli_1)

    font_2 = TTFont('./fonts/2.woff')
    cli_2 = [1, 3, 2, 7, 6, 8, 9, 0, 4, 5]
    coor_info_2 = get_coor_info(font_2, cli_2)

    font_3 = TTFont('./fonts/3.woff')
    cli_3 = [5, 8, 3, 0, 6, 7, 9, 1, 2, 4]
    coor_info_3 = get_coor_info(font_3, cli_3)

    font_4 = TTFont('./fonts/4.woff')
    cli_4 = [9, 3, 4, 8, 7, 5, 2, 1, 6, 0]
    coor_info_4 = get_coor_info(font_4, cli_4)

    font_5 = TTFont('./fonts/5.woff')
    cli_5 = [1, 5, 8, 0, 7, 9, 6, 3, 2, 4]
    coor_info_5 = get_coor_info(font_5, cli_5)

    infos = coor_info_1 + coor_info_2 + coor_info_3 + coor_info_4 + coor_info_5
    return infos

import numpy as np
import pandas as pd
from maoyan.font import get_font_data
from sklearn.impute import SimpleImputer
from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier
from sklearn.preprocessing import StandardScaler


def main() -> None:
    # 处理缺失值
    imputer = SimpleImputer(missing_values=np.nan, strategy='mean')
    data = pd.DataFrame(imputer.fit_transform(pd.DataFrame(get_font_data())))
    # 取出特征值\目标值
    x = data.drop([0], axis=1)
    y = data[0]
    # 分割数据集
    # x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=0)
    x_train = x.head(30)
    y_train = y.head(30)
    x_test = x.tail(10)
    y_test = y.tail(10)
    # 标准化
    # std = StandardScaler()
    # x_train = std.fit_transform(x_train)
    # x_test = std.transform(x_test)
    # 进行算法流程
    knn = KNeighborsClassifier(n_neighbors=1)
    # 开始训练
    knn.fit(x_train, y_train)
    # 预测结果
    y_predict = knn.predict(x_test)
    print(y)
    # 得出准确率
    print(knn.score(x_test, y_test))

def get_board() -> None:
    map_dict = get_map(
        text=requests.get(
            url=_board_url,
            headers=_headers
        ).text
    )
    for uni in map_dict.keys():
        text = text.replace(uni, map_dict[uni])
    html = etree.HTML(text)
    dd_li = html.xpath('//dl[@class="board-wrapper"]/dd')
    for dd in dd_li:
        p_li = dd.xpath(
            './div[@class="board-item-main"]//div[@class="movie-item-info"]/p')
        title = p_li[0].xpath('./a/@title')[0]
        star = p_li[1].xpath('./text()')[0]
        releasetime = p_li[2].xpath('./text()')[0]
        p_li = dd.xpath(
            './div[@class="board-item-main"]//div[@class="movie-item-number boxoffice"]/p')
        realtime_stont = ''.join(
            list(map(lambda x: x.strip(), p_li[0].xpath('.//text()'))))
        total_stont = ''.join(
            list(map(lambda x: x.strip(), p_li[1].xpath('.//text()'))))
        print(title)
        print(star)
        print(releasetime)
        print(realtime_stont)
        print(total_stont)
        print('-' * 50)


get_board()