Python爬虫----------------免费爬取站长工具第一页长尾关键词

Python爬虫----------------免费爬取站长工具第一页长尾关键词

有句话说的好，白嫖它不香吗，废话不多说直接上代码

import urllib.request as request
import lxml.html as html
import time
import requests
from bs4 import BeautifulSoup
from openpyxl import load_workbook, workbook
from lxml import etree
import xlwt
from pyquery import PyQuery as pq



def search_keyword(keyword):
    a = 1
     i=1
    num =[]
    word=[]
     wb = workbook.Workbook()  # 创建Excel对象
    ws = wb.active  # 获取当前正在操作的表对象
    # 往表中写入标题行,以列表形式写入！
    k = 0
    ws.append(['序号', '长尾词', '指数'])
    while a <= 1:
        url = 'https://data.chinaz.com/keyword/allindex/%s/%s' % (keyword, a)
        print(url)
        requests.packages.urllib3.disable_warnings()
        data = requests.get(url, verify=False)

        soup = BeautifulSoup(data.text, 'lxml')  # 将爬取的网页以字符串的形式传入
        lilist = soup.find_all('li',class_="w60") # 选中class选择器
        linkss = soup.find_all('em', class_="blue2")
        for lin in range(1,len(linkss)):
                if lin<=len(linkss):
                    num.append(linkss[lin].text)
                lin += 2
        for aa in range(1,len(lilist)):

                word.append(lilist[aa].text)
        a += 1
        time.sleep(3)
    for k in range(0, len(word)):  # 按行插入数据到表中
        ws.append([k + 1, word[k],num[k]])
    wb.save(f'F:/{keyword}.xlsx')
    print(f"保存关键词数据为 {keyword}.xls 成功！")

if __name__ == '__main__':
    keyword = input('请输入关键词>>')
    print('正在查询，请稍后...')
    search_keyword(keyword)