Javascript逆向分析 猿人学 第四题 雪碧图 样式干扰

# # -*- coding: utf-8 -*- # # import re # # import execjs # import requests # from ddddocr import DdddOcr # from pyquery import PyQuery as pq # # ocr = DdddOcr() # with open('yuanrenxue.js', 'r', encoding='utf-8') as f: # jscode = f.read() # ctx = execjs.compile(jscode) # # headers = { # "accept": "application/json, text/javascript, */*; q=0.01", # "accept-language": "en-US,en;q=0.9,zh-CN;q=0.8,zh;q=0.7", # "referer": "https://match.yuanrenxue.cn/match/4", # "user-agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36", # "x-requested-with": "XMLHttpRequest" # } # # url = "https://match.yuanrenxue.cn/api/match/4" # params = { # "page": "1" # } # response = requests.get(url, headers=headers, cookies=None, params=params) # json_data = response.json() # items = pq(json_data['info'])('td').items() # key, value = json_data['key'], json_data['value'] # for item in items: # imgs = item('img.img_number').items() # md5_value = ctx.call('yrx_md5', {"key": key, "value": value}) # data = {} # for i, img in enumerate(imgs): # img_class = img.attr('class') # if md5_value in img_class: # continue # style = re.findall(r'-?\d+\.?\d*', img.attr('style'))[0] # b64 = re.sub('data:image/png;base64,', '', img.attr('src')).strip() # num = ocr.classification(b64) # data[i] = (style, num) # print(data) # -*- coding: utf-8 -*- import re import execjs import requests from ddddocr import DdddOcr from pyquery import PyQuery as pq from loguru import logger class YuanRenXueMatch(object): def __init__(self): self.ocr = DdddOcr() with open('yuanrenxue.js', 'r', encoding='utf-8') as f: self.jscode = f.read() self.ctx = execjs.compile(self.jscode) self.headers = { "accept": "application/json, text/javascript, */*; q=0.01", "accept-language": "en-US,en;q=0.9,zh-CN;q=0.8,zh;q=0.7", "referer": "https://match.yuanrenxue.cn/match/4", "user-agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36", "x-requested-with": "XMLHttpRequest" } self.url = "https://match.yuanrenxue.cn/api/match/4" def rearrange_and_convert(self, data: dict) -> int: tmp_data = {k + int(float(v[0]) / 11.5): v[1] for k, v in data.items()} sorted_values = [v for k, v in sorted(tmp_data.items())] num_str = ''.join(sorted_values) return int(num_str) def fetch_data(self, page): params = {"page": str(page)} # url = self.base_url.format(page=page) logger.debug('Fetching page: {}'.format(page)) response = requests.get(self.url, headers=self.headers, params=params) return response.json() def process_data(self, data): items = pq(data['info'])('td').items() key, value = data['key'], data['value'] for item in items: imgs = item('img.img_number').items() md5_value = self.ctx.call('yrx_md5', {"key": key, "value": value}) result = {} index = 0 for img in imgs: img_class = img.attr('class') if md5_value in img_class: continue style = re.findall(r'-?\d+\.?\d*', img.attr('style'))[0] b64 = re.sub('data:image/png;base64,', '', img.attr('src')).strip() num = self.ocr.classification(b64) result[index] = (style, num) index += 1 num_value = self.rearrange_and_convert(result) logger.debug('原始数值：{}'.format(str(result))) logger.debug('调整后数值：{}'.format(num_value)) yield num_value def main(self): sum = 0 for page in range(1, 6): json_data = self.fetch_data(page) for num_value in self.process_data(json_data): sum += num_value logger.debug('5页的全部数字加和：{}'.format(sum)) @classmethod def run(cls): YuanRenXueMatch().main() if __name__ == "__main__": YuanRenXueMatch.run()