crawl_baidu/crawl_baidu/crawl_baidu.py

#!/usr/bin/env python
# -*- encoding: utf-8 -*-
'''
@Contact :   liuyuqi.gov@msn.cn
@Time    :   2022/06/28 23:15:05
@License :   Copyright © 2017-2022 liuyuqi. All Rights Reserved.
@Desc    :   
'''

from http import cookies
import requests
import sys,os,json
from crawl_baidu.lib.json_conf import JsonConf
import time
headers = {
    'Accept': 'application/json, text/plain, */*',
    'Accept-Encoding': 'gzip, deflate',
    'Accept-Language': 'zh-CN,zh;q=0.9',
    'Cache-Control': 'no-cache',
    'DNT': '1',
    'Host': 'index.baidu.com',
    'Pragma': 'no-cache',
    'Proxy-Connection': 'keep-alive',
    'Referer': 'https://index.baidu.com/v2/main/index.html',
    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.90 Safari/537.36',
    'X-Requested-With': 'XMLHttpRequest',
}

class CrawlBaidu():
    def __init__(self):
        self.sess=requests.Session()
        self.jsonConf = JsonConf()
        self.conf = self.jsonConf.load()
        cookie = self.conf.get('cookie')
        CliperText = self.conf.get('CliperText')
        self.words = self.conf.get('words')
        # self.sess.cookies.update(cookie)
        self.sess.headers.update({
            "Cipher-Text":CliperText,
            "Cookie" : cookie
            })

    @staticmethod
    def decrypt(t,e):
        n = list(t)
        i = list(e)
        a = {}
        result = []
        ln = int(len(n)/2)
        start = n[ln:]
        end = n[:ln]
        for j,k in zip(start, end):
            a.update({k: j})
        for j in e:
            result.append(a.get(j))
        return ''.join(result)
        
    def get_ptbk(self,uniqid):
        url = 'http://index.baidu.com/Interface/ptbk?uniqid={}'
        resp = self.sess.get(url.format(uniqid), headers=headers)
        if resp.status_code != 200:
            print('获取uniqid失败')
            sys.exit(1)
        return resp.json().get('data')
        
    def get_index_data(self, start='2011-01-03', end='2022-08-05'):
        keyword = str(self.words).replace("'", '"')
        url = f'http://index.baidu.com/api/SearchApi/index?area=0&word={keyword}&area=0&startDate={start}&endDate={end}'
        resp = self.sess.get(url, headers=headers)
        if resp.status_code != 200:
            print('获取指数失败')
            sys.exit(1)

        content = resp.json()
        data = content.get('data')
        user_indexes = data.get('userIndexes')[0]
        uniqid = data.get('uniqid')
        ptbk = self.get_ptbk(uniqid)

        while ptbk is None or ptbk == '':
            ptbk = self.get_ptbk(uniqid)

        all_data = user_indexes.get('all').get('data')
        result = CrawlBaidu.decrypt(ptbk, all_data)
        result = result.split(',')

        print(result)

        if  not os.path.exists("data"):
            os.mkdir("data")
        with open("data/res.txt","w") as file:
            file.write(json.dumps(result))