Mobile Suica Python Extractor

suica.py

import requests
import bs4
import re
import datetime

print("JRE Mobile Suica History Extractor v0.1")
print("Developed by @tomo0611_dev\n")

session = requests.Session()


class SuicaHistory:
    def __init__(
        self,
        date,
        in_type,
        in_station,
        out_type,
        out_station,
        balance,
        amount,
    ):
        self.date = date
        self.in_type = in_type
        self.in_station = in_station
        self.out_type = out_type
        self.out_station = out_station
        self.balance = balance.replace("\\", "").replace(",", "")
        self.amount = amount.replace(",", "")

    def as_csv(self):
        return f"{self.date},{self.in_type},{self.in_station},{self.out_type},{self.out_station},{self.balance},{self.amount}"

    def __str__(self):
        return f"{self.date} {self.in_type} {self.in_station} {self.out_type} {self.out_station} {self.balance} {self.amount}"


def save_image(url, file_path):
    response = session.get(
        url,
        headers={
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36",
        },
    )
    with open(file_path, "wb") as file:
        file.write(response.content)


print("[MobileSuica] Start login process")

url = "https://www.mobilesuica.com/index.aspx"
response = session.get(
    url,
    headers={
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36",
    },
)

# find form with beautifulsoup
soup = bs4.BeautifulSoup(response.text, "html.parser")
form = soup.find("form", id="form1")

# find image and save it
print("[MobileSuica] Getting captcha image and save it\n")
image = form.find("img")
save_image("https://www.mobilesuica.com/" + image["src"], "captcha.png")

post_url_action = form.get("action")
# print(post_url_action)
# list input fields
input_fields = form.find_all("input")
data = {}
for input_field in input_fields:
    data[input_field.get("name")] = input_field.get("value")
# print(data)

print("You need to login to Mobile Suica")

data["MailAddress"] = input("Enter your email: ")
data["Password"] = input("Enter your password: ")
print("View captcha.png and enter captcha code")
captcha_code = input("Enter captcha: ")
data["WebCaptcha1_clientState"] = "[[[[null]],[],[]],[{},[]],null]"
data["WebCaptcha1__editor_clientState"] = (
    "|0|01" + captcha_code + '||[[[[]],[],[]],[{},[]],"01' + captcha_code + '"]'
)
data["WebCaptcha1__editor"] = captcha_code
data["LOGIN"] = "%83%8D%83O%83C%83%93"

print("")
print("[MobileSuica] Post login data to server")

response = session.post(
    "https://www.mobilesuica.com/" + post_url_action,
    data=data,
    headers={
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36",
    },
)

# ログイン可否の判定
if "<title>JR東日本：モバイルSuica＞会員メニュー</title>" not in response.text:
    print("[MobileSuica] Login failed")
    exit(1)

# ログイン成功
print("[MobileSuica] Authentication successful")
# find post url
soup = bs4.BeautifulSoup(response.text, "html.parser")
href = (
    soup.find("div", id="btn_sfHistory")
    .find("a")
    .attrs["href"]
    .replace("javascript:StartApplication('", "")
    .replace("')", "")
)

print("[MobileSuica] Redirect to business function (ViewHistory)")
# 業務機能へ転送遷移
response = session.post(
    href,
    headers={
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36",
    },
)

# find text javascript:StartApplication('https://www.mobilesuica.com/iq/ir/SuicaDisp.aspx?returnId=SFRCMMEPC03')
href = re.search(r"javascript:StartApplication\('(.+?)'\)", response.text).group(1)
print("[MobileSuica] Get history data\n")
response = session.post(
    href,
    headers={
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36",
    },
)

# get historyTable
soup = bs4.BeautifulSoup(response.text, "html.parser")
empty_elem = bs4.BeautifulSoup("<font></font>", "html.parser").find("font")
history_table = soup.find("td", attrs={"class": "historyTable"}).find_all("tr")
histiory_list = []
for row in history_table:
    # find font with sentence
    data = row.find_all("font")
    if len(data) != 7:
        data = [
            data[0],
            empty_elem,
            empty_elem,
            empty_elem,
            empty_elem,
            empty_elem,
            empty_elem,
        ]

    history_item = SuicaHistory(
        data[0].text.strip(),
        data[1].text.strip(),
        data[2].text.strip(),
        data[3].text.strip(),
        data[4].text.strip(),
        data[5].text.strip(),
        data[6].text.strip(),
    )

    histiory_list.append(history_item)

    print(history_item)

print("\n[MobileSuica] Save history data to history.csv")
with open(
    "history_" + datetime.datetime.now().strftime("%Y%m%d") + ".csv",
    "w",
    encoding="shift-jis",
) as file:
    for history in histiory_list:
        file.write(history.as_csv() + "\n")