文章目录
Gitee仓库地址:travel-server:景点旅游项目服务端
3.基于Python中的Selenium爬取携程旅游网景点详细数据
3.1前提环境
- 确保安装python3.x环境
- 以管理员身份打开cmd,安装selenium、pymysql、datetime,默认安装最新版即可
pip install selenium
pip install pymysql
pip install datetime
- 确保chrome安装对应版本的驱动(将该驱动放在chrome安装路径下),用于控制chrome浏览器,并将路径添加到环境变量的Path变量中,如图所示!
#安装chrome驱动教程链接:https://blog.csdn.net/linglong_L/article/details/136283810
3.2思路
- 搜索指定城市景点,网站通过分页进行展示;
- 使用selenium每个景点的详细访问路径,并点击该路径获取详细景点信息,再通过正则表达式获取需要的内容;
- 如下图,景点的详细信息有:景点名称、景点等级(1-5A)、景点地址、开放时间(有两种,我们采用下面的)、联系电话、景点介绍、景点图片等内容
3.3代码详讲
3.3.1查询指定城市的所有景点
- 控制打开chrome,并访问指定查询所有景点路径
def__init__(self):
options = Options()
options.add_argument('--headless')
service = Service()
self.chrome = Chrome(service=service)
self.chrome.get('https://huodong.ctrip.com/things-to-do/list?pagetype=city&citytype=dt&keyword=%E6%A2%85%E5%B7%9E&id=523&name=%E6%A2%85%E5%B7%9E&pshowcode=Ticket2&kwdfrom=srch&bookingtransactionid=1711160613361_6064')
time.sleep(3)
self.page =1
self.headers ={'cookie':'suid=lh/P1+4RKuhAYg684ErS+g==; suid=lh/P1+4RKuhAYg684ErS+g==','user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.116 Safari/537.36',}
3.3.2获取详细景点的访问路径
- 使用selenium的根据class定位元素方法,找到详细景点的href属性,即为该景点的访问路径
- 并通过page属性控制访问的页数
#获取景点请求路径defget_url(self):whileTrue:
content = self.chrome.find_element(By.CLASS_NAME,"right-content-list").get_attribute('innerHTML')
cons = re.findall(r'href="(.*?)" title="(.*?)"', content)for con in cons:
self.detail_url ='https:'+ con[0]
self.title = con[1]print(self.detail_url, self.title)
self.get_detail()
self.chrome.find_element(By.CLASS_NAME,'u_icon_enArrowforward').click()
time.sleep(1)
self.page +=1if self.page ==120:break
3.3.3获取景点的详细信息
- 景点的详细信息有:景点名称、景点等级(1-5A)、景点地址、开放时间(有两种,我们采用下面的)、联系电话、景点介绍、景点图片等内容
- 通过正则表达式获取,详细代码如下:
- 并每次获取详细信息之后,将信息保存到mysql数据库中
defget_detail(self):
detail_con = requests.get(self.detail_url, verify=False, headers=self.headers).text
# time.sleep(2)'''使用正则获取信息'''
self.title =''.join(re.findall(r'<div class="title"><h1>(.*?)<', detail_con, re.DOTALL))print('景点名称:'+self.title)#self.rank = ''.join(re.findall(r'rankText">(.*?)<', detail_con, re.DOTALL))
self.address =''.join(re.findall(r'地址</p><p class="baseInfoText">(.*?)<', detail_con, re.DOTALL))
self.mobile =''.join(re.findall(r'官方电话</p><p class="baseInfoText">(.*?)<', detail_con, re.DOTALL))
self.quality_grade=''.join(re.findall(r'<div class="titleTips"><span>(.*?)<!--', detail_con, re.DOTALL))#self.openTime = ''.join(re.findall(r'开放时间</div><div class="moduleContent">(.*?)<', detail_con, re.DOTALL))
first_three_characters = self.address[:3]print('所在省份城市:'+'广东省'+first_three_characters)print('详细地址:'+self.address)#print('开放时间:'+self.openTime)print('电话:'+self.mobile)print('等级:'+self.quality_grade)if self.quality_grade=='':
self.quality_grade=0'''使用xpath获取信息'''
ret = etree.HTML(detail_con)
desc_cons = ret.xpath('//div[@class="detailModule normalModule"]//div[@class="moduleContent"]')
desc_titles = ret.xpath('//div[@class="detailModule normalModule"]//div[@class="moduleTitle"]')
desc_list =[]
desc_title_list =[]for d in desc_cons:
des =''.join(d.xpath('.//text()'))
desc_list.append(des)for d in desc_titles:
des =''.join(d.xpath('.//text()'))
desc_title_list.append(des)
desc_dict =dict(zip(desc_title_list, desc_list))#print(desc_dict)
first_value =list(desc_dict.values())[:2]# 获取前两个值iflen(first_value)>=1:
introduction = first_value[0]else:
introduction =''iflen(first_value)>=2:
opening_hours = first_value[1]else:
opening_hours =''print('介绍:'+introduction)print('开放时间:'+ opening_hours)'''获取图片链接'''
img_list =[]
imgs = re.findall(r'background-image:url\((.*?)\)', detail_con, re.DOTALL)for img in imgs:'''匹配到的同一张图片会有两种尺寸,我们只要大图,所以把尺寸为521*391的匹配出来即可'''
image = re.search(r'521_391', img)if image:
img_list.append(img)print(",".join(img_list))
conn = pymysql.connect(host='localhost', user='root', password='root',
database='travel_ams', charset='utf8mb4')
cursor = conn.cursor()
sql ="INSERT INTO ams_attraction (attraction_name, quality_grade, province_city, location, open_hour, phone, introduction, images, add_time) VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s)"
values =(self.title, self.quality_grade,'广东省'+first_three_characters, self.address, opening_hours, self.mobile, introduction,",".join(img_list),datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S"))
cursor.execute(sql, values)
conn.commit()
conn.close()#self.get_ticket()
3.4数据库设计
travel_ams数据库的ams_attraction表
字段名字段类型是否为主键是否有唯一约束是否有非空约束注释attraction_idint是景点id,自增attraction_namevarchar(20)景点名称resource_type_idint景点资源类型idquality_gradeint景点等级province_cityvarchar(20)景点所在省份城市locationvarchar(1000)详细位置open_hourvarchar(1000)开放时间phonevarchar(1000)电话introductionvarchar(10000)景点介绍imagesvarchar(1000)景点图片列表stausint状态【1为显示,0为不显示】add_timedatetime添加时间update_timedatetime修改时间
创建表语句如下:
CREATETABLE ams_attraction (
attraction_id INTPRIMARYKEYAUTO_INCREMENTCOMMENT'景点id,自增',
attraction_name VARCHAR(20)COMMENT'景点名称',
resource_type_id INTCOMMENT'景点资源类型id',
province_city VARCHAR(20)COMMENT'景点所在省份城市',
location VARCHAR(1000)COMMENT'详细位置',
open_hour VARCHAR(1000)COMMENT'开放时间',
phone VARCHAR(1000)COMMENT'电话',
introduction VARCHAR(10000)COMMENT'景点介绍',
images VARCHAR(1000)COMMENT'景点图片列表',statusINTCOMMENT'状态【1为显示,0为不显示】',
add_time DATETIMECOMMENT'添加时间',
update_time DATETIMECOMMENT'修改时间');
3.5全部代码
- 执行该main方法,即可完成导入指定访问路径的景点数据
- 可以在控制台查询是否导入成功
import pandas
import re
import time
import requests
import urllib3
from lxml import etree
from selenium.webdriver import Chrome
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.common.by import By
import pymysql
import datetime
urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)classJy_jd(object):def__init__(self):
options = Options()
options.add_argument('--headless')
service = Service()
self.chrome = Chrome(service=service)
self.chrome.get('https://huodong.ctrip.com/things-to-do/list?pagetype=city&citytype=dt&keyword=%E6%A2%85%E5%B7%9E&id=523&name=%E6%A2%85%E5%B7%9E&pshowcode=Ticket2&kwdfrom=srch&bookingtransactionid=1711160613361_6064')
time.sleep(3)
self.page =1
self.headers ={'cookie':'suid=lh/P1+4RKuhAYg684ErS+g==; suid=lh/P1+4RKuhAYg684ErS+g==','user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.116 Safari/537.36',}#获取景点请求路径defget_url(self):whileTrue:
content = self.chrome.find_element(By.CLASS_NAME,"right-content-list").get_attribute('innerHTML')
cons = re.findall(r'href="(.*?)" title="(.*?)"', content)for con in cons:
self.detail_url ='https:'+ con[0]
self.title = con[1]print(self.detail_url, self.title)
self.get_detail()
self.chrome.find_element(By.CLASS_NAME,'u_icon_enArrowforward').click()
time.sleep(1)
self.page +=1if self.page ==120:breakdefget_detail(self):
detail_con = requests.get(self.detail_url, verify=False, headers=self.headers).text
# time.sleep(2)'''使用正则获取信息'''
self.title =''.join(re.findall(r'<div class="title"><h1>(.*?)<', detail_con, re.DOTALL))print('景点名称:'+self.title)#self.rank = ''.join(re.findall(r'rankText">(.*?)<', detail_con, re.DOTALL))
self.address =''.join(re.findall(r'地址</p><p class="baseInfoText">(.*?)<', detail_con, re.DOTALL))
self.mobile =''.join(re.findall(r'官方电话</p><p class="baseInfoText">(.*?)<', detail_con, re.DOTALL))
self.quality_grade=''.join(re.findall(r'<div class="titleTips"><span>(.*?)<!--', detail_con, re.DOTALL))#self.openTime = ''.join(re.findall(r'开放时间</div><div class="moduleContent">(.*?)<', detail_con, re.DOTALL))
first_three_characters = self.address[:3]print('所在省份城市:'+'广东省'+first_three_characters)print('详细地址:'+self.address)#print('开放时间:'+self.openTime)print('电话:'+self.mobile)print('等级:'+self.quality_grade)if self.quality_grade=='':
self.quality_grade=0'''使用xpath获取信息'''
ret = etree.HTML(detail_con)
desc_cons = ret.xpath('//div[@class="detailModule normalModule"]//div[@class="moduleContent"]')
desc_titles = ret.xpath('//div[@class="detailModule normalModule"]//div[@class="moduleTitle"]')
desc_list =[]
desc_title_list =[]for d in desc_cons:
des =''.join(d.xpath('.//text()'))
desc_list.append(des)for d in desc_titles:
des =''.join(d.xpath('.//text()'))
desc_title_list.append(des)
desc_dict =dict(zip(desc_title_list, desc_list))#print(desc_dict)
first_value =list(desc_dict.values())[:2]# 获取前两个值iflen(first_value)>=1:
introduction = first_value[0]else:
introduction =''iflen(first_value)>=2:
opening_hours = first_value[1]else:
opening_hours =''print('介绍:'+introduction)print('开放时间:'+ opening_hours)'''获取图片链接'''
img_list =[]
imgs = re.findall(r'background-image:url\((.*?)\)', detail_con, re.DOTALL)for img in imgs:'''匹配到的同一张图片会有两种尺寸,我们只要大图,所以把尺寸为521*391的匹配出来即可'''
image = re.search(r'521_391', img)if image:
img_list.append(img)print(",".join(img_list))
conn = pymysql.connect(host='localhost', user='root', password='root',
database='travel_ams', charset='utf8mb4')
cursor = conn.cursor()
sql ="INSERT INTO ams_attraction (attraction_name, quality_grade, province_city, location, open_hour, phone, introduction, images, add_time) VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s)"
values =(self.title, self.quality_grade,'广东省'+first_three_characters, self.address, opening_hours, self.mobile, introduction,",".join(img_list),datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S"))
cursor.execute(sql, values)
conn.commit()
conn.close()#self.get_ticket()#获取门票defget_ticket(self):id= self.detail_url.split('/')[-1]print(id)
ticket_url =f'https://piao.ctrip.com/ticket/dest/{id}?onlyContent=true&onlyShelf=true'
ticket_res = requests.get(ticket_url, verify=False, headers=self.headers).text
# time.sleep(1)
ticket_ret = etree.HTML(ticket_res)
ticket = ticket_ret.xpath('//table[@class="ticket-table"]//div[@class="ttd-fs-18"]/text()')
price = ticket_ret.xpath('//table[@class="ticket-table"]//td[@class="td-price"]//strong[@class="ttd-fs-24"]/text()')print(ticket)print(price)'''拿到的列表里可能存在不确定数量的空值,所以这里用while True把空值全部删除,这样才可以确保门票种类与价格正确对应上'''whileTrue:try:
ticket.remove(' ')except:breakwhileTrue:try:
price.remove(' ')except:break'''
这里多一个if判断是因为我发现有些详情页即便拿到门票信息并剔除掉空值之后仍然存在无法对应的问题,原因是网页规则有变动,
所以一旦出现这种情况需要使用新的匹配规则,否则会数据会出错(不会报错,但信息对应会错误)
'''iflen(ticket)!=len(price):
ticket = ticket_ret.xpath('//table[@class="ticket-table"]/tbody[@class="tkt-bg-gray"]//a[@class="ticket-title "]/text()')
price = ticket_ret.xpath('//table[@class="ticket-table"]//strong[@class="ttd-fs-24"]/text()')whileTrue:try:
ticket.remove(' ')except:breakwhileTrue:try:
price.remove(' ')except:breakprint(ticket)print(price)
ticket_dict =dict(zip(ticket, price))print(ticket_dict)if __name__ =='__main__':
jy_jd = Jy_jd()
jy_jd.get_url()
3.6效果图
版权归原作者 闲来踢桃 所有, 如有侵权,请联系我们删除。