import requests
from lxml import etree
import xlwt


def getData():
    datalist=[]         # 总的数据列表
    headers = {
        'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36',
    }
    # 获取页面源码
    url = 'https://weixin.qq.com/'
    page_text = requests.get(url=url, headers=headers).text
    # 数据解析
    tree = etree.HTML(page_text)
    li_list = tree.xpath('/html/body/div/div/div[2]/div[3]/ul/li')  # 将li对象列表赋值给li_list变量
    # 循环遍历列表对象
    for li in li_list:
        data = []       #每行数据的列表
        title = li.xpath('./a/text()')[0]  # /text()：获取的是标签中直系的文本内容
        data.append(title)
        date = li.xpath('./span/text()')[0]
        data.append(date)
        datalist.append(data)       #将每行列表添加到总列表

    return datalist


def saveData(datalist, savepath):
    print('save....')
    book = xlwt.Workbook(encoding='utf-8')
    sheet = book.add_sheet('sht1', cell_overwrite_ok=True)
    col = ('标题', '日期')
    for i in range(0, len(col)):            #元组是不可变的，len取长度
        sheet.write(0, i, col[i])     #列名
    for i in range(0, len(datalist)):       #使用len(列表）获得长度
        data = datalist[i]
        for j in range(0, len(data)):
            sheet.write(i+1, j, data[j])
    book.save(savepath)
    print('save ok....')


if __name__ == "__main__":
    savepath='aaa2.xls'
    datalist = getData()
    saveData(datalist, savepath)