python挖掘chinaz长尾词脚本代码分享

最新推荐文章于 2023-04-16 11:49:45 发布

淘小白_TXB2196

最新推荐文章于 2023-04-16 11:49:45 发布

阅读量647

点赞数

文章标签：大数据

本文链接：https://blog.csdn.net/u012917925/article/details/125674908

版权

chinaz的长尾词挖掘需要付费，有个入口是可以白票到一部分长尾词的，淘小白这里只做了一个简单的小脚本，需要改进的朋友可以自行改进一下，直接上代码：

# -*- coding: utf-8 -*-

'''

@作者 淘小白
@联系QQ 1290654348
@VX:TXB2196
@官网 i-uni.cn

'''
import os
import time
import re
import requests
headers ={
	
	'Accept': 'application/json, text/javascript, */*; q=0.01',
	'Accept-Encoding': 'gzip, deflate, br',
	'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8',
	'Connection': 'keep-alive',
	'Content-Length': '29',
	'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
	'Cookie': '==================！！！！换成自己的cookie ！！！！==================',
	'Host': 'data.chinaz.com',
	'Origin': 'https://data.chinaz.com',
	'Referer': 'https://data.chinaz.com/ci',
	'sec-ch-ua': '" Not A;Brand";v="99", "Chromium";v="101", "Google Chrome";v="101"',
	'sec-ch-ua-mobile': '?0',
	'sec-ch-ua-platform': '"Windows"',
	'Sec-Fetch-Dest': 'empty',
	'Sec-Fetch-Mode': 'cors',
	'Sec-Fetch-Site': 'same-origin',
	'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/101.0.0.0 Safari/537.36',
	'X-Requested-With': 'XMLHttpRequest'
}
def get_chinaz_ci(key):
	url = 'https://data.chinaz.com/pull/allkeyword'
	datas = {
		'keyword': key
	}

	req = requests.post(url,data=datas,headers=headers)
	res = req.text
	ci_ku = re.findall(r'"(.*?)"',res)
	return ci_ku

def write_key(key):
	with open('D:\\淘金网\\chinaz 词库\\待修改_ciku.txt','a+') as f:
		if '带货' in key :
			f.write(key+'\n')
			print(key)
		else:
			pass

def get_list_key(key):
	url = 'https://data.chinaz.com/pull/indexkeyword'
	datas = {
		'keyword': key
	}

	req = requests.post(url,data=datas,headers=headers)
	res = req.text
	ci_ku = re.findall(r'"(.*?)"',res)
	return ci_ku


if __name__ == '__main__':


	zc_ku = []
	ci_all = []
	key = '新手带货'
	zc_ku.append(key)
	ci_all.append(key)
	while True:
		if len(zc_ku) > 0:
			del_key= zc_ku.pop(0)
			xl_ci = get_chinaz_ci(del_key)
			xg_ci = get_list_key(del_key)
			xg_cis = xl_ci+xg_ci
			for i in xg_cis:
				if i not in ci_all:
					zc_ku.append(i)
					ci_all.append(i)
					write_key(i)
					
				else:
					pass
			if len(zc_ku)<0:
				break
			else:
				pass
		else:
			print('Done!')
			break