python版问答聚合采集工具源代码+反编译完美还原
该工具可以通过头条搜索、百度下拉结果、搜狗下拉、百度知道搜索、新浪爱问、搜狗问问来进行组合标题答案构成文章。
该python文件已反编译完美还原源代码，亲测有效。python问答聚合采集。
源代码如下:
import configparser
import json
import threading
from queue import Queue
from urllib import request
from urllib.parse import quote
import os
import random
import re
import requests
import time
from lxml import etree
config = configparser.RawConfigParser()
config.read('peizhi.ini')
ZHANGHAO = config.get('KUANDAI', 'ZHANGHAO')
MIMA = config.get('KUANDAI', 'MIMA')
IP = int(config.get('KUANDAI', 'IP'))
KD_QUEUE = Queue(1000000)
web_ck = config.get('KUANDAI', 'web_ck')
FOREGROUND_RED = 0x0c # red.
FOREGROUND_GREEN = 0x0a # green.
FOREGROUND_BLUE = 0x09 # blue.
CHA = ''
with open('替换词库.txt', 'r', encoding='utf8') as (f):
tihuan_list = f.read().split('\n')
def connect():
cmd_str = 'rasdial %s %s %s' % ('宽带连接', ZHANGHAO, MIMA)
os.system(cmd_str)
print('拨号')
time.sleep(2)
def disconnect():
cmd_str = 'rasdial 宽带连接 /disconnect'
os.system(cmd_str)
print('断开链接')
time.sleep(2)
def get_connect():
header_baidu = {
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/69.0.3497.100 Safari/537.36'}
try:
code = requests.get('http://apps.game.qq.com/comm-htdocs/ip/get_ip.php', headers=header_baidu,
timeout=5).status_code
if code != 200:
connect()
else:
disconnect()
time.sleep(5)
connect()
except:
disconnect()
time.sleep(5)
connect()
def get_toutiao_urls(wd):
url = 'https://so.toutiao.com/search?keyword=' + wd + '&pd=question&source=search_subtab_switch&dvpf=pc&aid=4916&page_num=0'
headers = {'Cache-Control': 'no-cache',
'Connection': 'keep-alive',
'Cookie': web_ck,
'Host': 'so.toutiao.com',
'Pragma': 'no-cache',
'Referer': 'https://so.toutiao.com/search?keyword=seo&pd=question&source=search_subtab_switch&dvpf=pc&aid=4916&page_num=0',
'sec-ch-ua-mobile': '?0',
'Sec-Fetch-Dest': 'document',
'Sec-Fetch-Mode': 'navigate',
'Sec-Fetch-Site': 'same-origin',
'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/91.0.4472.124 Safari/537.36'}
res = requests.get(url=url, headers=headers)
res.encoding = 'utf8'
title_list = re.findall('"title":"(.*?)",', res.text)
title_list = [i for i in title_list if '\\' not in i]
url_list = re.findall('"url":"(.*?)","', res.text)
url_list = [i for i in url_list if 'wukong' in i]
return [i.replace('http:', 'https:') for i in url_list], title_list
def get_wukong_content(url):
headers = {'accept-encoding': 'gzip, deflate, br',
'accept-language': 'zh-CN,zh;q=0.9,zh-TW;q=0.8,en-US;q=0.7,en;q=0.6',
'cache-control': 'no-cache',
'pragma': 'no-cache',
'sec-ch-ua-mobile': '?0',
'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/91.0.4472.124 Safari/537.36'}
try:
res = requests.get(url=url, headers=headers)
if res.status_code == 200:
res.encoding = 'utf8'
wenzhang_list = \
json.loads(re.findall('INITIAL_STATE__=([\\s\\S]*?)