买房指南，链家最近房源

# coding=utf-8

"""
Author: nieliangcai
version: 0.1

date: 2019/7/29 11:30
"""

import requests_html
import xlwt
import time
import openpyxl
from pprint import pprint


now_time = time.strftime("%Y%m%d%H%M")
session = requests_html.HTMLSession()

House_List = ["徐泾北城", "泗泾", "佘山", "九亭", "宝龙广场", "洞泾", "蟠龙路", "宝山"]


def write_house_data(table_info, title="地区房价%s.xlsx" % now_time):
    """
    :param table_info: 所有内容
    :param title: filename
    :return:
    """
    # print(table_info)
    # 创建一个空的Workbook，并且删除默认的Sheetname
    file = openpyxl.Workbook()
    file.remove(file["Sheet"])
    # file = xlwt.Workbook()

    for i in range(len(table_info)):
        """sheet_name和单元格内容"""
        address = table_info[i][0]
        Values = table_info[i][1]

        # 使用抓到的数据做sheet_name
        table = file.create_sheet(address)
        # table = file.add_sheet(address)
        title_list = ['Title', 'house_info', 'height', 'total_price', 'unit_price']
        # 写数据从1开始
        for i in range(5):
            table.cell(1, i+1, title_list[i])

        # print(Values)
        for i in range(len(Values)):
            for j in range(len(Values[i])):
                # print(Values[i][j])
                table.cell(i + 2, j+1, Values[i][j])
    file.save(title)


all_house = []
for house in House_List:
    URL = "https://sh.lianjia.com/ershoufang/rs%s/" % house
    res = session.get(URL)
    title_all = res.html.find(".title>a")  # 获取标题信息
    house_info_all = res.html.find(".houseInfo")  # 房源信息
    position_Info_all = res.html.find(".positionInfo")  # 位置
    totalPrice = res.html.find(".totalPrice")  # 总价
    unitPrice = res.html.find(".unitPrice")  # 单价

    list_house = []
    for i in range(len(title_all)):
        list_house.append([title_all[i].text, house_info_all[i].text, position_Info_all[i].text, totalPrice[i].text,
                           unitPrice[i].text])
    all_house.append(list_house)

zipped = list(zip(House_List, all_house))
pprint(zipped)
write_house_data(zipped)