python爬取网页存入到Excel

from requests_html import HTMLSession
import xlwt

# 建立会话
session = HTMLSession()
url = 'https://www.jianshu.com/p/85f4624485b9'
read = session.get(url)
select = 'body > div.note > div.post > div.article > div.show-content > div > p > a'
def get_url_element(select):
    url_list = []
    url_element = read.html.find(select)
    try:
        for result in url_element:
            # 返回网页元素 对应的文字描述
            get_text = result.text
            # 将返回数组转为list  返回HTML中的绝对路径链接
            get_links = list(result.absolute_links)[0]
            url_list.append(get_text)
            url_list.append(get_links)
        return url_list
    except:
        None
# 创建Excel对象
workExcel = xlwt.Workbook()
# 添加表名
sheet = workExcel.add_sheet('sheet')
data = get_url_element(select)
# 将list转化为dictionary
df = dict(zip(data[0::2],data[1::2]))
row = 0
# 迭代字典
for i,j in df.items():
    sheet.write(row,0,i)
    sheet.write(row,1,j)
    row += 1
workExcel.save('E:\\firstExcel\\output.xls')

转载于:https://my.oschina.net/u/3867704/blog/3024564