pythonjs解析去哪儿_Python+Selenium爬取去哪儿网信息

from selenium import webdriver

from selenium.webdriver.common.by import By

from selenium.webdriver.support.ui import WebDriverWait

from selenium.webdriver.support import expected_conditions as EC

from selenium.webdriver.common.keys import Keys

import time

from bs4 import BeautifulSoup

import xlwt

class QunarSpider():

def theSpider(self, city, startdate, enddate,totalpagenum):

driver = webdriver.Firefox()

driver.get("https://hotel.qunar.com")

# 选取城市

toCity = driver.find_element_by_xpath("//input[@tabindex='1']")

toCity.clear()

toCity.send_keys(city)

element = WebDriverWait(driver, 10).until(EC.presence_of_element_located((By.CLASS_NAME, "hot_key_list")))

toCity.send_keys(Keys.TAB)

time.sleep(2)

# 选取结束日期

checkOutDate = driver.find_element_by_xpath("//input[@tabindex='3']")

checkOutDate.click()

checkOutDate.send_keys(Keys.CONTROL, "a")

checkOutDate.send_keys(Keys.DELETE)

checkOutDate.send_keys(enddate)

# 选取开始日期

checkInDate = driver.find_element_by_xpath("//input[@tabindex='2']")

checkInDate.click()

checkInDate.send_keys(Keys.CONTROL, "a")

checkInDate.send_keys(Keys.DELETE)

checkInDate.send_keys(startdate)

# 进行搜索

search = driver.find_element_by_xpath("//a[@tabindex='5']")

search.click()

# 页面解析，并创建数据列表

# 酒店序号

num = 1

page_num = 1

totalPageNum = 5

contentList = []

for l in range(0,totalPageNum):

time.sleep(2)

html = driver.page_source

soup = BeautifulSoup(html, "html.parser", from_encoding='utf-8')

infos = soup.find_all('div', class_="inner clearfix")

for info in infos:

content = info.select("div > div > p > a")

# 打印店名及价格

print(content[1].text, "——————————", content[0].text)

contentSgl = [num, content[1].text, content[0].text, '2020-07-18', '2020-07-19']

contentList.append(contentSgl)

num += 1

# 解析多页

nextPage = driver.find_element_by_xpath("//p[@class='next fl_right cur able']")

nextPage.click()

page_num += 1

# 创建Excel表，并写入数据

# 创建Excel表

f = xlwt.Workbook()

# 创建一个sheet对象，命名为“酒店信息”，cell_overwrite_ok表示是否可以覆盖单元格，是Worksheet实例化的一个参数，默认值是False

sheet1 = f.add_sheet('酒店信息', cell_overwrite_ok=True)

# 标题信息行列表

rowTitle = ['序号', '酒店名称', '价格', '入住如期', '离店日期']

# 遍历写入标题行信息

for i in range(0, len(rowTitle)):

# 其中的'0'表示行, 'i'表示列，0和i指定了表中的单元格，'rowTitle[i]'是向该单元格写入的内容

sheet1.write(0, i, rowTitle[i])

# 遍历写入数据信息

# 先遍历一下有多少行

for k in range(0, len(contentList)):

# 再把每行的每个单元格遍历一下，j表示列数据

for j in range(0, len(contentList[k])):

# k+1表示先去掉标题行，j表示列数据，contentList[k][j] 插入单元格数据

sheet1.write(k + 1, j, contentList[k][j])

f.save('D:/HInfo.xls')

if __name__=='__main__':

spider = QunarSpider()

city = input("请输入城市：")

startdate = input("请输入入住日期(yyyy-mm-dd):")

enddate = input("请输入离店日期(yyyy-mm-dd):")

totalpagenum = input("请输入爬取页数：")

print("正在爬取中...")

spider.theSpider(city, startdate, enddate,totalpagenum)