# 导入相关模块
import requests
from bs4 import BeautifulSoup
import pandas as pd


def getHtml(url):
    # 判断爬取 是否出错
    try:
        # 使用get方式爬取页面,添加头部伪装浏览器
        r = requests.get(url, headers={‘user-agent‘: ‘Mozilla/5.0‘})

        r.raise_for_status()
        # 设置编码格式
        r.encoding = r.apparent_encoding
        # 返回源码
        return r.text
    except:
        return "页面爬取Error"

def HotelList(text,hotellist):

    soup = BeautifulSoup(text, "html.parser")
    # 爬取酒店列表
    hotel_list = soup.select("div#hotel_list>div")
    # 循环
    for hotel in hotel_list:
        # 将可能出现错误的地方进行跳过
        try:
            # 酒店名称
            hotel_name = hotel.select("h2")[0].text
            # 酒店链接
            href = hotel.select("h2>a")[0].attrs["href"]
            # 服务贫家
            recommend = hotel.select("span.recommend")[0].text
            p = hotel.select("p.hotel_item_htladdress")
            # 酒店地址
            dizhi = p[0].text
            # 最新预定时间
            newtime = hotel.select("p.hotel_item_last_book")[0].text
            # 评分
            hotel_score = hotel.find_all("span", "hotel_value")[0].text
            # 点评人数
            people_number = hotel.select("span.hotel_judgement>span")[0].text
            # 酒店评分
            level = hotel.find_all("span", "hotel_level")[0].text
            # 质量保证
            ico_quality_gold = hotel.select("span.ico_quality_gold")[0].text
            # 所属地区
            diqu = p[0].find_all(
                "a", attrs={"tracekey": "nhtllistroomclick"})[0].text
            # price = hotel.find_all("span", "J_price_lowList ")[0].text
            
            hotellist.append([hotel_name, href, recommend, dizhi, newtime, 
                              hotel_score, people_number, level, ico_quality_gold, diqu])
            print([hotel_name, href, recommend, dizhi, newtime,
                   hotel_score, people_number, level, ico_quality_gold, diqu])

        except:
            "一个数据爬取出错"
            hotellist.append([hotel_name, href, recommend, dizhi, newtime, 
                              hotel_score, people_number, level, ico_quality_gold, diqu])


def savedata(hotellist):

    wri = pd.ExcelWriter("HotelList.xlsx")

    col = ["hotel_name", "href", "recommend", "dizhi", "newtime",
           "hotel_score", "people_number", "level", "ico_quality_gold", "diqu"]

    pf = pd.DataFrame(hotellist,columns=col)
    # 写入excel
    pf.to_excel(wri)

    wri.save()

def main():
    # 存放数据的数组
    hotellist = []
    text = getHtml(
        "https://hotels.ctrip.com/hotel/quanzhou406#ctm_ref=hod_hp_sb_lst")

    HotelList(text, hotellist)
    #打印结果信息
    print(hotellist)
    # 数据保存
    savedata(hotellist)