仿站长之家的源码_Python爬虫工具，站长之家网站关键词采集及导出

Python爬虫工具，站长之家网站关键词采集及导出

#站长之家网站关键词采集

import requests
from lxml import etree
import xlsxwriter

def hqsj(url):
    #url="http://rank.chinaz.com/?host=www.ugainian.com"
    html=requests.get(url).text
    #print(html)
    nr=etree.HTML(html)
    #print(nr)
    keywords=nr.xpath('//div[@class="w25-0 tl pl10 pr pbimg showt"]/a/text()') #关键字
    #print(keywords)
    datas=nr.xpath('//div[@class="w8-0"]/a/text()')
    #print(datas)
    overall_index=datas[0::4] #整体指数
    #overall_index=datas[::4])
    pc_index=datas[1::4] #pc指数
    mobile_index=datas[2::4] #移动指数
    baidu_ranking=datas[3::4] #百度排名
    #print(overall_index)
    #print(pc_index)
    #print(mobile_index)
    #print(baidu_ranking)
    collection=nr.xpath('//div[@class="w8-0 bor-r1s05"]/a/text()') #收录量
    #print(collection)
    title=[]
    link=[]
    title_datas=nr.xpath('//div[@class="R-home-w"]/a')
    for title_data in title_datas:
        #print(title_data.attrib)
        title.append(title_data.attrib['title']) #网页标题
        links=title_data.attrib['onclick'] #网页链接
        links=links.replace('window.open',"")
        links =links[2:]
        links = links[:-2]
        #print(links)
        link.append(links)

    #print(title)
    #print(link)

    for keywords,overall_index,pc_index,mobile_index,baidu_ranking,collection,title,link in zip (keywords,overall_index,pc_index,mobile_index,baidu_ranking,collection,title,link):
        data=[keywords,overall_index,pc_index,mobile_index,baidu_ranking,collection,title,link]
        #print(data)

    return data





def hqlj(wz):
    url=f"http://rank.chinaz.com/?host={wz}"
    html=requests.get(url).text
    #print(html)
    nr=etree.HTML(html)
    #print(nr)
    page=nr.xpath('/html/body/form/div[2]/div[3]/div[1]/div[2]/span[1]/text()')
    print(page)
    ljs=[]
    if not page:
        ljs.append(url)
    else:
        page=page[0]
        page=page.replace("共","")
        page=page.replace("页，到第","")
        page=int(page)
        print(page)

        for x in range(1,page+1):
            lj=f'http://rank.chinaz.com/{wz}-0--0-{x}'
            print(lj)
            ljs.append(lj)
    #print(ljs)
    return ljs

if __name__ == '__main__':
    wz=input("请输入网址链接：")
    urls=hqlj(wz)
    data_list = []
    for url in urls:
        #print(url)
        dat=hqsj(url)
        print(dat)
        data_list.append(dat)

    print(data_list)

    workbook = xlsxwriter.Workbook('e:kami1.xlsx')  # 创建一个Excel文件
    worksheet = workbook.add_worksheet()  # 创建一个sheet

    title = ['关键字', '整体指数', 'pc指数', '移动指数', '百度排名', '收录量', '网页标题', '网页链接']  # 表格title
    worksheet.write_row('A1', title)  # title 写入Excel

    for index, da in enumerate(data_list):
        num0 = str(index + 2)
        row = 'A' + num0
        worksheet.write_row(row, da)
    workbook.close()