公司背景
某国际航班特价平台，针对某猪网，通过配置始发地、目的地、时间等自动筛选出价格最低的单程国际航班，最后导出Excel格式的航班信息
fly.gif
开发技术
Python+pyppeteer
开发步骤
- 配置筛选条件
[查询条件]
始发城市 = 贵阳
目的地城市 = 曼谷
始发日期 = 2020-03-15
天数 = 2
总时间小于 = 18
起飞时间段 = 00:00-24:00
到达时间段 = 00:00-03:00,09:00-24:00
- 登录账户
为了安全起见，账号、密码并没有存储，第一次登录需要手动输入账号，登录成功之后会保存cookie，下次运行的时候直接加载cookie打开网址，就不需要再重复输入账号来登录
@run
async def login(self):
iframe_ele = await self.spider.driver.J('.sufei-dialog')
if iframe_ele != None and (await iframe_ele.isIntersectingViewport()):
return False
cookies = await self.spider.get_cookie()
with open(os.path.join(LOCAL_PATH, 'cookies.json'), 'w+') as f:
f.write(cookies)
return True
- 键入筛选条件搜索航班
@run
async def search(self):
form_ele = await self.spider.driver.J('#J_IeSearch')
type_ele = await form_ele.J('#J_search-type')
search_eles = await form_ele.JJ('.search-con')
for item in search_eles:
label_eles = await item.JJ('label')
for x in label_eles:
span_ele = await x.J('span')
if (await get_text(span_ele)) == '出发日期':
date_input = await x.J('input')
break
from_input = await form_ele.J('.J_DepCityCode')
to_input = await form_ele.J('.J_ArrCityCode')
type_value = await get_attribute(type_ele, 'value')
from_value = await get_attribute(from_input, 'value')
to_value = await get_attribute(to_input, 'value')
date_value = await get_attribute(date_input, 'value')
btn_ele = await form_ele.J('.search-btn')
if type_value == '0' and self.check_code(self.spider.city[0], from_value) and self.check_code(self.spider.city[1], to_value) and date_value == self.spider.curr_date:
await btn_ele.click()
return True
await type_ele.click()
await type_ele.click()
await self.spider.driver.select('#J_search-type', '0')
await self.keyboard_input(self.spider.city[0])
await self.spider.driver.keyboard.press('Tab')
await self.keyboard_input(self.spider.city[1])
await self.spider.driver.keyboard.press('Tab')
await self.keyboard_input(self.spider.curr_date)
await self.spider.driver.select('#J_search-type', '0')
return False
- 解析网页内容
先对所有航班信息进行价格从低到高排序，然后记录满足条件的第一个航班，再跳转下一天，重复进行直到到达结束日期为止
@run
async def parse_item(self):
container_ele = await self.spider.driver.J('#J_DepResultContainer')
list_ele = await container_ele.xpath('div')
if len(list_ele) == 0:
self.change_state(StateType.search)
return
price_list = []
for i in range(len(list_ele)):
item = list_ele[i]
quantity_ele = await item.J('.quantity')
if quantity_ele and (await get_text(quantity_ele)).find('张') != -1:
num = re.findall(r'[0-9]+', (await get_text(quantity_ele)))
if len(num) > 0:
if int(num[0]) <= 4:
continue
tips_ele = await item.J('.tips-info')
if tips_ele and (await get_text(tips_ele)).find('过境签') != -1:
continue
if tips_ele and (await get_text(tips_ele)).find('需换机场') != -1:
continue
if tips_ele and (await get_text(tips_ele)).find('中转需重新值机托运') != -1:
continue
- 保存数据到Excel
def write_data(self, _from, _to, _date, _time, _price):
self.spider.sheet.write(self.spider.row_index, 0, _to)
self.spider.sheet.write(self.spider.row_index, 1, _from)
self.spider.sheet.write(self.spider.row_index, 2, _date)
self.spider.sheet.write(self.spider.row_index, 3, _time)
self.spider.sheet.write(self.spider.row_index, 4, _price)
self.spider.book.save(self.spider.out_path)
self.spider.row_index += 1
WX20200308-162627.png
