火车票买不到?看我用python监控票源
2019-12-18 18:01 zouhui 阅读(341) 评论(0) 收藏 举报同时说最近火车票难买,我就帮他用个脚本监控 一下。
最近高铁票比较难买,还有什么候补。要不停的刷,才有时候可以捡漏。有时候明明候补了,到快开车告诉你余票不足,候补失败。
凡事预则立,我打算写个脚本提前两个星期就监控起来,这样就可以提高买到票的几率了。
先是考虑用接口,发现行不通,手动打开页面都OK,就是接口调不到数据。只好曲线救国,用selenium打开页面,用BeautifulSoup来获取页面内容。发现打开页面后,可以直接用数据清洗。大概的代码是这样的:
import timefrom selenium import webdriverfrom selenium.webdriver.common.by import Byfrom selenium.webdriver.support import expected_conditions as ECfrom selenium.webdriver.support.select import Selectfrom selenium.webdriver.support.wait import WebDriverWaitfrom bs4 import BeautifulSoupimport pandasimport arrow
Max_Time_Out = 30Time_Out = 10sh_to_sz = "18002400"sz_to_sh = "06001200"sh_to_sz_train = "G7026|G7260|G7062|G7226|G7028"sh_station = 'cc_from_station_上海_check'sz_to_sh_train = "D3125|G7001|G7037|G7039"sz_station = 'cc_from_station_苏州_check'
time_id = "cc_start_time"now = arrow.now().format('YYYY-MM-DD HH:MM:SS')
option = webdriver.ChromeOptions()
option.add_argument('disable-infobars')# option.binary_location="/Applications/AppleTools /Google Chrome.app/Contents/MacOS/Google Chrome"option.add_argument('headless')
sh_to_sz_url = "https://kyfw.12306.cn/otn/leftTicket/init?linktypeid=dc&fs=%E4%B8%8A%E6%B5%B7,SHH&ts=%E8%8B%8F%E5%B7%9E,SZH&date={}&flag=N,N,Y"sz_to_sh_url = "https://kyfw.12306.cn/otn/leftTicket/init?linktypeid=dc&fs=%E8%8B%8F%E5%B7%9E,SZH&ts=%E4%B8%8A%E6%B5%B7,SHH&date={}&flag=N,N,Y"
driver = webdriver.Chrome(chrome_options=option)
driver.set_page_load_timeout(Max_Time_Out)
def open_page(url): try: driver.get(url) except TimeoutError: print("cannot open the page for {} seconds".format(Max_Time_Out)) driver.execute_script('window.stop()')
def find_element(obj): WebDriverWait(driver, Time_Out).until(EC.visibility_of_element_located((By.ID, obj))) element = WebDriverWait(driver, Time_Out).until(lambda x: driver.find_element(By.ID, obj)) return element
def type(obj, value): find_element(obj).clear() find_element(obj).send_keys(value)
def clickat(obj): WebDriverWait(driver, Time_Out).until(EC.element_to_be_clickable((By.ID, obj))) find_element(obj).click()
def toggle_checkbox(station_id): inputs = driver.find_elements_by_tag_name("input") for input in inputs: if input.get_attribute("value") == 'G': input.click() if input.get_attribute("value") == 'D': input.click() if input.get_attribute("id") == station_id: input.click()
def get_today(): today = arrow.now() if today.weekday() not in [5, 6]: return today.format('YYYY-MM-DD')
def get_next_day(): next_day = arrow.now().shift(days=+1) if next_day.weekday() not in [5, 6]: return next_day.format('YYYY-MM-DD')
def get_next_two_monday(): next_two_monday = [arrow.now().shift(days=x).format('YYYY-MM-DD') for x in range(1, 15) if arrow.now().shift(days=x).weekday() == 0] return next_two_monday
def get_next_two_friday(): next_two_friady = [arrow.now().shift(days=x).format('YYYY-MM-DD') for x in range(1, 15) if arrow.now().shift(days=x).weekday() == 4] return next_two_friady
def select_time(obj, time_zone, station_id): '''
:param driver: :param obj: :return:
<select class="select-small" id="cc_start_time"> <option value="00002400">00:00--24:00</option><option value="00000600">00:00--06:00</option><option value="06001200">06:00--12:00</option><option value="12001800">12:00--18:00</option><option value="18002400">18:00--24:00</option></select> '''
start_time = find_element(obj) get_start = Select(start_time) get_start.select_by_value(time_zone) toggle_checkbox(station_id) time.sleep(3)
def get_trains(url, city_time, station_id, trains): open_page(url) select_time(time_id, city_time, station_id) ht = driver.page_source html_pd = pandas.read_html(ht)
pd = html_pd[1]
pd3 = pd[pd['车次'].str.contains(trains, na=False)]
coloum_list = ["车次", "二等座", "无座"] # print(pd3[coloum_list])
return pd3[coloum_list] if __name__ == "__main__": today = get_today() next_day = get_next_day() mondays = get_next_two_monday() fridays = get_next_two_friday()
df_list = [] # next_suzhou_to_shanghai = get_trains(sz_to_sh_url.format(next_day), sz_to_sh, sz_station, sz_to_sh_train) df_list.append(next_suzhou_to_shanghai) today_shanghai_to_suzhou = get_trains(sh_to_sz_url.format(today), sh_to_sz, sh_station, sh_to_sz_train) df_list.append(today_shanghai_to_suzhou)
suzhou_to_shanghai_next_monday = get_trains(sz_to_sh_url.format(mondays[0]), sz_to_sh, sz_station, sz_to_sh_train) df_list.append(suzhou_to_shanghai_next_monday)
suzhou_to_shanghai_next_next_monday = get_trains(sz_to_sh_url.format(mondays[1]), sz_to_sh, sz_station, sz_to_sh_train) df_list.append(suzhou_to_shanghai_next_next_monday) #
shanghai_to_suzhou_next_friday = get_trains(sh_to_sz_url.format(fridays[0]), sh_to_sz, sh_station, sh_to_sz_train) df_list.append(shanghai_to_suzhou_next_friday)
shanghai_to_suzhou_next_next_friday = get_trains(sh_to_sz_url.format(fridays[1]), sh_to_sz, sh_station, sh_to_sz_train) df_list.append(shanghai_to_suzhou_next_next_friday)
driver.quit()把自己需要乘坐的车次,日期给设定好,当然我这边主要是要算周五跟周一,监控了两个星期的这两天。设置好定时,给自己发邮件。
然后发邮件,大概样子是这样的:
这样上班的时候,就收到邮件,就可以择机买票了。
现在来聊聊,处理web页面,可能用到哪些库。
python对web的操作常用到的库:请求库,解析库,存储库,工具库
1. 请求库
urllib/re是python默认自带的库
Python内置的Http请求库urllib.request 请求模块 模拟浏览器urllib.error 异常处理模块urllib.parse url解析模块 工具模块,如:拆分、合并urllib.robotparser robots.txt 解析模块 例子:
超时测试
import urllib.request
response =urllib.request.urlopen('http://httpbin.org/get',timeout=1)
print(response.read())
-----正常
import socket
import urllib.reqeust
import urllib.error
try:
response=urllib.request.urlopen('http://httpbin.org/get',timeout=0.1)
except urllib.error.URLError as e:
if isinstance(e.reason,socket.timeout):
print('TIME OUT')
这是就是输出 TIME OUTRequest 可以添加headers
import urllib.request
request=urllib.request.Request('https://python.org')
response=urllib.request.urlopen(request)
print(response.read().decode('utf-8'))例子:
from urllib import request,parse
url='http://httpbin.org/post'
headers={
User-Agent:Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.75 Safari/537.36 Host:httpbin.org }
dict={
'name':'Germey'
}
data=bytes(parse.urlencode(dict),encoding='utf8')
req= request.Request(url=url,data=data,headers=headers,method='POST')
response = request.urlopen(req)
print(response.read().decode('utf-8'))代理
import urllib.request
proxy_handler =urllib.request.ProxyHandler({
'http':'http://127.0.0.1:9743',
'https':'http://127.0.0.1:9743',
})
opener =urllib.request.build_opener(proxy_handler)
response= opener.open('http://httpbin.org/get')
print(response.read())
Cookie
import http.cookiejar,urllib.request
cookie = http.cookiejar.Cookiejar()
handler=urllib.request.HTTPCookieProcessor(cookie)
opener = urllib.request.build_opener(handler)
response = opener.open('http://www.baidu.com')
for item in cookie:
print(item.name+"="+item.value)第一种保存cookie方式
import http.cookiejar,urllib.request
filename = 'cookie.txt'
cookie =http.cookiejar.MozillaCookieJar(filename)
handler= urllib.request.HTTPCookieProcessor(cookie)
opener=urllib.request.build_opener(handler)
response= opener.open('http://www.baidu.com')
cookie.save(ignore_discard=True,ignore_expires=True)(2) requests
pip3 install requests(3) selenium
pip3 install selenium2. 解析库:
2.1 lxml (XPATH)
pip3 install lxmltest, test.html指上述实例
直接读取内容
from lxml import etreehtml = etree.HTML(test)直接读取文件
from lxml import etreehtml = etree.parse(test.html)2.2 beautifulsoup
pip3 install beautifulsoup4验证
from bs4 import BeautifulSoupsoup = BeautifulSoup('<html></html>','lxml')2.3 pyquery(类似jquery语法)
pip3 install pyquery注意:由于 pyquery 依赖于 lxml ,要先安装 lxml ,否则会提示失败。验证安装结果
from pyquery import PyQuery as pqdoc = pq('<html>hi</html>')result = doc('html').text()有 4 种方法可以进行初始化:可以通过传入 字符串、lxml、文件 或者 url 来使用PyQuery。
from pyquery import PyQuery as pqfrom lxml import etree
d = pq("<html></html>")#传入字符串d = pq(etree.fromstring("<html></html>"))#传入lxmld = pq(url=‘http://google.com/‘) #传入urld = pq(filename=path_to_html_file) #传入文件1、.html() 和.text():获取相应的 HTML 块或者文本内容,
p=pq("<head><title>Hello World!</title></head>")
print p(‘head‘).html()# 获取相应的 HTML 块print p(‘head‘).text()# 获取相应的文本内容输出:
<title>hello</title>Hello World!2、.(‘selector‘):通过选择器来获取目标内容,
d = pq("<div><p id=‘item-0‘>test 1</p><p class=‘item-1‘>test 2</p></div>")
print d(‘div‘).html()# 获取 <div> 元素内的 HTML 块print d(‘#item-0‘).text()# 获取 id 为 item-0 的元素内的文本内容print d(‘.item-1‘).text()# 获取 class 为 item-1 的元素的文本内容输出:
<p id="item-0">test 1</p><p class="item-1">test 2</p>test 1test 23、.eq(index):根据索引号获取指定元素(index 从 0 开始),
d = pq("<div><p id=‘item-0‘>test 1</p><p class=‘item-1‘>test 2</p></div>")
print d(‘p‘).eq(1).text()# 获取第二个 p 元素的文本内容,输出 test 2
4、.find():查找嵌套元素,
d = pq("<div><p id=‘item-0‘>test 1</p><p class=‘item-1‘>test 2</p></div>")
print d(‘div‘).find(‘p‘) # 查找 <div> 内的 p 元素print d(‘div‘).find(‘p‘).eq(0) # 查找 <div> 内的 p 元素,输出第一个 p 元素输出:
<p id="item-0">test 1</p><p class="item-1">test 2</p><p id="item-0">test 1</p>5、.filter():根据 class、id 筛选指定元素,
d = pq("<div><p id=‘item-0‘>test 1</p><p class=‘item-1‘>test 2</p></div>")
print d(‘p‘).filter(‘.item-1‘) # 查找 class 为 item-1 的 p 元素print d(‘p‘).filter(‘#item-0‘) # 查找 id 为 item-0 的 p 元素输出:
<p class="item-1">test 2</p><p id="item-0">test 1</p>6、.attr():获取、修改属性值,
d = pq("<div><p id=‘item-0‘>test 1</p><a class=‘item-1‘>test 2</p></div>")
print d(‘p‘).attr(‘id‘) # 获取 <p> 标签的属性 idprint d(‘a‘).attr(‘class‘,‘new‘)# 修改 <a> 标签的 class 属性为 new输出:
item-0<a class="new">test 2</a>7、其他操作:
.addClass(value):添加 class;.hasClass(name):判断是否包含指定的 class,返回 True 或 False;.children():获取子元素;.parents():获取父元素;.next():获取下一个元素;.nextAll():获取后面全部元素块;.not_(‘selector‘):获取所有不匹配该选择器的元素;for i in d.items(‘li‘): print i.text():遍历 d 中的 li 元素;3. 存储库
3.1 pymysql(操作MySQL,关系型数据库) 安装:
pip3 install pymysql3.2 pymongo(操作MongoDB,key-value) 安装
pip3 install pymongo3.3 redis(分布式爬虫,维护爬取队列) 安装:
pip3 install redis生活中的点滴小时,用技术来辅助,就可以让生活更加美好了!
浙公网安备 33010602011771号