python scraping print also show []

Question

I want to get this page's timetable but my code the end print is [].

How can I get the time table use Beautiful soup?

This is my page https://www.thsrc.com.tw/ArticleContent/a3b630bb-1066-4352-a1ef-58c7b4e8ef7c

The end print also show[]

What tags or class should I use?

from selenium import webdriver
from selenium.webdriver.support.ui import Select


import pandas as pd
import time
import requests as req
from bs4 import BeautifulSoup


url="https://www.thsrc.com.tw/ArticleContent/a3b630bb-1066-4352-a1ef-58c7b4e8ef7c"
driver=webdriver.Chrome()

driver.get(url)

ag=driver.find_element_by_class_name("swal2-confirm.swal2-styled")
ag.click()


#start
def start():
    print("請輸入起始站")
    start=Select(driver.find_element_by_id("select_location01"))
    all_option=start.select_by_visible_text(input(""))
start()


#terminal
def stand():
    print("terminal")
    stand=Select(driver.find_element_by_id("select_location02"))
    all_option2=stand.select_by_visible_text(input(""))
stand()

#search
sr=driver.find_element_by_id("start-search")
sr.click()




soup = BeautifulSoup(driver.page_source, "lxml")

dan=[]
data=soup.find_all("div","timeTableTrain_S")
dan.append(data)
print(dan)



time.sleep(5)

driver.quit()

user_10035985 · Answer

Looking at the site it's better to use their API (the data is loaded from this API using JavaScript). This example will print all train/station info, departure and destination tables:

import json
import requests

api_url = "https://www.thsrc.com.tw/TimeTable/Search"

payload = {
    "SearchType": "S",
    "Lang": "TW",
    "StartStation": "NanGang",
    "EndStation": "ZuoYing",
    "OutWardSearchDate": "2022/05/20",
    "OutWardSearchTime": "10:30",
    "ReturnSearchDate": "2022/05/20",
    "ReturnSearchTime": "10:30",
    "DiscountType": "",
}

data = requests.post(api_url, data=payload).json()

print(json.dumps(data, indent=4))

Prints:

{
    "success": true,
    "data": {
        "DepartureTable": {
            "Title": {
                "StartStationName": "\u5357\u6e2f",
                "EndStationName": "\u5de6\u71df",
                "TitleSplit1": "2022/05/20(\u4e94) 10:30",
                "TitleSplit2": "2022/05/20(\u4e94)"
            },
            "TrainItem": [
                {
                    "TrainNumber": "0803",
                    "DepartureTime": "06:15",
                    "DestinationTime": "08:40",
                    "Duration": "02:25",
                    "NonReservedCar": "10-12",
                    "Discount": [
                        {
                            "Id": "9973b559-8279-4bf4-90be-601f7973a39f",
                            "Name": "20\u4eba\u5718\u9ad4",
                            "Value": "8\u6298",
                            "Color": "#1685e4",
                            "Discount": "80"
                        },
                        {
                            "Id": "68d9fc7b-7330-44c2-962a-74bc47d2ee8a",
                            "Name": "\u5927\u5b78\u751f",
                            "Value": "5\u6298",
                            "Color": "#e45916",
                            "Discount": "5"
                        },
                        {
                            "Id": "40863ff1-a16c-4da1-8af7-c1f8991627f3",
                            "Name": "\u6821\u5916\u6559\u5b78",
                            "Value": "4/7\u6298",
                            "Color": "#ffcc00",
                            "Discount": "40|70"
                        }
                    ],
                    "Note": "",
                    "Sequence": 0,
                    "StationInfo": [
                        {
                            "StationNo": "01",
                            "StationName": "\u5357\u6e2f",
                            "DepartureTime": "06:15",
                            "Show": true,
                            "ColorClass": "orange"
                        },

... and so on.

python scraping print also show []

1 Answers