python程序错误无法解决，请指导

zikai · 发表于 2023-7-19 21:35

道客巴巴.rar (4.84 KB, 下载次数: 14)

# !/usr/bin/env python
# -*- coding: utf-8 -*-
# ------------------------------
''''''

USER_AGENT_LIST = [
'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; Hot Lingo 2.0)',
'Mozilla/5.0 (Windows NT 6.2; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.90 Safari/537.36',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3451.0 Safari/537.36',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.9; rv:57.0) Gecko/20100101 Firefox/57.0',
'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1500.71 Safari/537.36',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.2999.0 Safari/537.36',
'Mozilla/5.0 (Windows NT 6.3; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.70 Safari/537.36',
'Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10.4; en-US; rv:1.9.2.2) Gecko/20100316 Firefox/3.6.2',
'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/44.0.2403.155 Safari/537.36 OPR/31.0.1889.174',
'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.1.4322; MS-RTC LM 8; InfoPath.2; Tablet PC 2.0)',
'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/48.0.2564.116 Safari/537.36 TheWorld 7',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36 OPR/55.0.2994.61',
'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; MATP; InfoPath.2; .NET4.0C; CIBA; Maxthon 2.0)',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.814.0 Safari/535.1',
'Mozilla/5.0 (Macintosh; U; PPC Mac OS X; ja-jp) AppleWebKit/418.9.1 (KHTML, like Gecko) Safari/419.3',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/43.0.2357.134 Safari/537.36',
'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; Trident/6.0; Touch; MASMJS)',
'Mozilla/5.0 (X11; Linux i686) AppleWebKit/535.21 (KHTML, like Gecko) Chrome/19.0.1041.0 Safari/535.21',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36',
'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; Hot Lingo 2.0)',
'Mozilla/5.0 (Windows NT 6.2; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.90 Safari/537.36',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3451.0 Safari/537.36',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.9; rv:57.0) Gecko/20100101 Firefox/57.0',
'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1500.71 Safari/537.36',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.2999.0 Safari/537.36',
'Mozilla/5.0 (Windows NT 6.3; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.70 Safari/537.36',
'Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10.4; en-US; rv:1.9.2.2) Gecko/20100316 Firefox/3.6.2',
'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/44.0.2403.155 Safari/537.36 OPR/31.0.1889.174',
'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.1.4322; MS-RTC LM 8; InfoPath.2; Tablet PC 2.0)',
'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/48.0.2564.116 Safari/537.36 TheWorld 7',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36 OPR/55.0.2994.61',
'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; MATP; InfoPath.2; .NET4.0C; CIBA; Maxthon 2.0)',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.814.0 Safari/535.1',
'Mozilla/5.0 (Macintosh; U; PPC Mac OS X; ja-jp) AppleWebKit/418.9.1 (KHTML, like Gecko) Safari/419.3',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/43.0.2357.134 Safari/537.36',
'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; Trident/6.0; Touch; MASMJS)',
'Mozilla/5.0 (X11; Linux i686) AppleWebKit/535.21 (KHTML, like Gecko) Chrome/19.0.1041.0 Safari/535.21',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36',
'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4093.3 Safari/537.36',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_5) AppleWebKit/537.36 (KHTML, like Gecko; compatible; Swurl) Chrome/77.0.3865.120 Safari/537.36',
'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36',
'Mozilla/5.0 (X11; Linux x86_64; rv:68.0) Gecko/20100101 Goanna/4.7 Firefox/68.0 PaleMoon/28.16.0',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.131 Safari/537.36',
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4086.0 Safari/537.36',
'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:75.0) Gecko/20100101 Firefox/75.0',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) coc_coc_browser/91.0.146 Chrome/85.0.4183.146 Safari/537.36',
'Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/537.36 (KHTML, like Gecko) Safari/537.36 VivoBrowser/8.4.72.0 Chrome/62.0.3202.84',
'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.101 Safari/537.36',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36 Edg/87.0.664.60',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.16; rv:83.0) Gecko/20100101 Firefox/83.0',
'Mozilla/5.0 (X11; CrOS x86_64 13505.63.0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.9; rv:68.0) Gecko/20100101 Firefox/68.0',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.101 Safari/537.36',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36',
'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36 OPR/72.0.3815.400',
'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.101 Safari/537.36',
]

import random, execjs, json, img2pdf
from requests_html import HTMLSession

class DkbbSpider(object):
def __init__(self):
      '''
         1、初始化部分
      '''
      self.session = HTMLSession()
      self.img_url = r'https://gif1.doc88.com/get-{}.gif'
      self.start_url = r'{}'.format(input('请输入下载文档网址:'))
      self.article_info_url = r'https://m.doc88.com/doc.php?act=info&p_code={' \
                              r'}&key=3854933de90d1dbb321d8ca29eac130a&v=1&pid='

def parse_get_article_id(self):
      '''
         2、解析获取文章ID
      '''
      article_id = self.start_url.split('-')[-1].split('.')[0]
      # print(article_id)
      self.requests_article_info_url(article_id)

def requests_article_info_url(self, article_id):
      '''
         3、请求获取加密数据
      '''
      headers = {'user-agent': random.choice(USER_AGENT_LIST)}
      response_first = self.session.get(self.article_info_url.format(article_id), headers=headers).content.decode()
      # print(response_first)
      self.Reverse_JS(response_first)

def Reverse_JS(self, response_first):
      '''
         4、JS逆向部分, 获取文章信息
      '''
      with open(r'dcbb.js', 'r', encoding='utf-8') as f:
         js_code = f.read()
      Decrypt_data = execjs.compile(js_code).call('Encrypt', response_first)
      # print(Decrypt_data)
      self.parse_Decrypt_data(Decrypt_data)

def parse_Decrypt_data(self, Decrypt_data):
      '''
         5、解析响应数据
      '''
      # ========================A、JSON数据转字典===================
      response_second = json.loads(Decrypt_data)
      # ========================B、解析数据=========================
      # 1、文章标题
      title = response_second['name']
      # 2、图片加密参数
      img_infos = response_second['gif_struct']
      img_infos = json.loads(img_infos)
      self.requests_img_url(img_infos, title)

def requests_img_url(self, img_infos, title):
      '''
         6、请求获取图片二进制数据
      '''
      img_content_list = []
      for img_info in img_infos:
         img_page = img_info['p']
         img_info = img_info['u']
         headers = {'user-agent': random.choice(USER_AGENT_LIST)}
         img_content = self.session.get(self.img_url.format(img_info), headers=headers).content
         # print(img_content)
         img_content_list.append(img_content)
         print(r'文档正在下载: {}.pdf -- 第{}页'.format(title, img_page))
      self.save_pdf_data(img_content_list, title)

def save_pdf_data(self, img_content_list, title):
      '''
         7、保存PDF文件
      '''
      # 1、设置PDF文件尺寸
      pdf_size = (img2pdf.mm_to_pt(720), img2pdf.mm_to_pt(1000))
      # 2、应用尺寸
      pdf_app = img2pdf.get_layout_fun(pdf_size)
      # 3、准备数据
      pdf_data = img2pdf.convert(img_content_list, layout_fun=pdf_app)
      # 4、保存数据
      with open('./{}.pdf'.format(title), 'wb') as f:
         f.write(pdf_data)
      print(r'道客巴巴Vip文档正在完成: {}.pdf'.format(title))

def main(self):
      '''
         逻辑控制部分
      '''
      self.parse_get_article_id()

if __name__ == '__main__':
dkbb = DkbbSpider()
dkbb.main()

Kris_Shin · 发表于 2023-7-19 22:22

看起来是你105行传入的response_first里面有execjs无法解析的字符, 还有下次写脚本尽量路径和文件名使用英文名

grekevin · 发表于 2023-7-19 22:31

你把dcbb.js用记事本打开，另存为UTF-8格式

zyjsuper · 发表于 2023-7-20 01:28

response_first = self.session.get(self.article_info_url.format(article_id), headers=headers).content.decode()
打印下这个值看看，或者设置decode编码为utf8

sai609 · 发表于 2023-7-20 08:08

这是网络爬虫？？？

ciker_li · 发表于 2023-7-20 09:45

dcbb.js发出来看看

白水饮 · 发表于 2023-7-20 10:21

js代码有问题

鹿鸣 · 发表于 2023-7-20 10:50

路径和文件名使用了中名吧

kof21411 · 发表于 2023-7-20 12:41

把dcbb.js里的中文注释全部去掉

magicianly · 发表于 2023-7-20 13:33

如果各位的方法你试过，都没有解决，那么你可以把这里改一下，试一下

帐号		自动登录	找回密码
密码			注册[Register]

[求助] python程序错误无法解决，请指导