259 lines
9.1 KiB
Python
259 lines
9.1 KiB
Python
# -*- coding: utf-8 -*-
|
||
"""
|
||
封装飞书客户端
|
||
"""
|
||
|
||
from email.parser import BytesParser
|
||
from email.policy import default
|
||
from email.utils import parsedate_to_datetime
|
||
from imaplib import IMAP4_SSL
|
||
import re
|
||
from time import time
|
||
from typing import Any, Dict, Optional, List
|
||
|
||
from authenticator import Authenticator
|
||
from request import Request
|
||
from base64 import b64encode
|
||
|
||
|
||
class Feishu:
|
||
"""飞书客户端"""
|
||
|
||
def __init__(self):
|
||
# 实例化认证器
|
||
self.authenticator = Authenticator()
|
||
# 实例化请求客户端
|
||
self.http_client = Request()
|
||
|
||
@staticmethod
|
||
def get_mail_verification_code(
|
||
folder: str, regular_expression: str
|
||
) -> Optional[str]:
|
||
"""
|
||
根据邮箱文件夹名获取邮箱验证码
|
||
:param folder: 邮箱文件夹名
|
||
:param regular_expression: 正则表达式
|
||
:return: 邮箱验证码
|
||
"""
|
||
"""
|
||
使用示例：
|
||
feishu = Feishu()
|
||
feishu.get_mail_verification_code(folder="邮箱验证码", regular_expression=r"【普康健康】您的验证码是：(\\d+)")
|
||
输出：123456
|
||
"""
|
||
if not folder:
|
||
raise RuntimeError("邮箱文件夹名不能为空")
|
||
|
||
# 若邮箱文件夹名不可ASCII编码（例如包含中文）则按照 IMAP 协议支持的字符串
|
||
try:
|
||
folder.encode("ascii")
|
||
except UnicodeEncodeError:
|
||
folder = f"&{b64encode(folder.encode(encoding="utf-16be")).decode(encoding="ascii").replace("/", ",").replace("+", "-").rstrip("=")}-"
|
||
|
||
try:
|
||
# 建立加密IMAP连接
|
||
connection = IMAP4_SSL(host="imap.feishu.cn", port=993)
|
||
# 登录
|
||
connection.login(user="mars@liubiren.cloud", password="aJBZSZzhQN13M11K")
|
||
except Exception as exception:
|
||
raise RuntimeError(f"登录邮箱发生异常：{str(exception)}")
|
||
|
||
# 开始时间戳（秒级，若无特殊说明时间戳均为秒级）
|
||
start_timestamp = time()
|
||
# 上一次查询时间戳
|
||
last_timestamp = 0
|
||
|
||
while True:
|
||
# 当前时间戳
|
||
current_timestamp = time()
|
||
|
||
# 若当前时间戳大于超时时间戳则登出并返回空
|
||
if current_timestamp > start_timestamp + 120:
|
||
connection.logout()
|
||
return None
|
||
|
||
# 若当前时间戳和上一次查询时间戳间隔小于5秒则跳转至下一次循环
|
||
if current_timestamp - last_timestamp < 5:
|
||
continue
|
||
|
||
last_timestamp = current_timestamp
|
||
|
||
# 选择邮箱文件夹
|
||
connection.select(mailbox=folder)
|
||
|
||
# 查询该邮箱文件夹内所有邮件
|
||
status, indices = connection.search(
|
||
"utf-8", "ALL"
|
||
) # search()返回形如 ('OK', [b'1 2 3 4 5']) 元组。其中，第一个元素为查询状态，第二个元素为查询结果（邮件索引的字节串列表）
|
||
# 若查询状态非成功则登出并抛出异常
|
||
if status != "OK":
|
||
connection.logout()
|
||
raise RuntimeError(f"查询邮箱文件夹内所有邮件失败")
|
||
|
||
# 拼接所有邮件索引并拆分为邮件索引列表
|
||
indices = b" ".join(indices).split()
|
||
# 若邮件索引列表为空则跳转至下一次循环
|
||
if not indices:
|
||
continue
|
||
|
||
# 查询该邮箱文件夹内最后一封邮件完整原始内容
|
||
status, contents = connection.fetch(indices[-1].decode("utf-8"), "(RFC822)")
|
||
# 若查询状态非成功则登出并抛出异常
|
||
if status != "OK":
|
||
connection.logout()
|
||
raise RuntimeError(f"查询邮箱文件夹内最后一封邮件完整原始内容失败")
|
||
|
||
contents = b"".join(
|
||
item[1] if isinstance(item, tuple) else item
|
||
for item in contents
|
||
if isinstance(item, (bytes, tuple))
|
||
and not (isinstance(item, bytes) and item == b")")
|
||
) # IMAP 协议中约定邮件完整原始内容中，第一个元素为二元组，形如 (b'5 (RFC822 {1234}', b'邮件字节') （第一个元素为元数据，第二个元素为第一部分内容），最后一个元素为结束符 b')'
|
||
# 若邮件内容为空则跳转至下一次循环
|
||
if not contents:
|
||
continue
|
||
|
||
# 解析邮件内容
|
||
contents = BytesParser(policy=default).parsebytes(text=contents)
|
||
# 邮件发送时间戳
|
||
send_timestamp = parsedate_to_datetime(contents["Date"]).timestamp()
|
||
# 若邮件发送时间戳小于开始时间戳减去冗余（近N秒）则跳转至下一次循环
|
||
if send_timestamp < start_timestamp - 300:
|
||
continue
|
||
|
||
for content in contents.walk():
|
||
# 若内容类型非 text/html 或 text/plain 则跳转至下一次循环
|
||
if content.get_content_type() not in ["text/plain", "text/html"]:
|
||
continue
|
||
|
||
# 获取内容载荷
|
||
payload = content.get_payload(decode=True)
|
||
match payload:
|
||
# 若内容载荷类型为字节串则解码
|
||
case _ if isinstance(payload, bytes):
|
||
payload = payload.decode(
|
||
encoding=content.get_content_charset() or "utf-8",
|
||
errors="replace",
|
||
)
|
||
case _ if isinstance(payload, str):
|
||
payload = payload
|
||
# 若内容为空则跳转至下一次循环
|
||
case _:
|
||
continue
|
||
|
||
matched = re.match(
|
||
pattern=regular_expression,
|
||
string=payload,
|
||
)
|
||
# 若未匹配到验证码则跳转至下一次循环
|
||
if not matched:
|
||
continue
|
||
|
||
connection.logout()
|
||
return matched.group(1)
|
||
|
||
def _get_headers(self) -> Dict[str, Any]:
|
||
"""
|
||
获取请求头
|
||
:return: 请求头
|
||
"""
|
||
return {
|
||
"Authorization": f"Bearer {self.authenticator.get_token(servicer='feishu')}",
|
||
}
|
||
|
||
# 获取多维表格记录
|
||
def get_bitable_records(
|
||
self,
|
||
app_token: str,
|
||
table_id: str,
|
||
) -> List[Dict[str, Any]]:
|
||
"""
|
||
获取多维表格记录
|
||
:param app_token: 多维表格应用标识
|
||
:param table_id: 多维表格数据表标识
|
||
:return: 多维表格记录
|
||
"""
|
||
# 构建多维表格查询记录的请求地址
|
||
url = f"https://open.feishu.cn/open-apis/bitable/v1/apps/{app_token}/tables/{table_id}/records/search" # https://open.feishu.cn/document/docs/bitable-v1/app-table-record/search 默认分页大小为 20
|
||
|
||
headers = self._get_headers()
|
||
# 添加 Content-Type 请求头
|
||
headers.update(
|
||
{
|
||
"Content-Type": "application/json; charset=utf-8",
|
||
}
|
||
)
|
||
|
||
records = [] # 用于临时保存多维表格记录
|
||
page_token = None # 分页标识
|
||
while True:
|
||
response = self.http_client.post(
|
||
url=(f"{url}?&page_token={page_token}" if page_token else url),
|
||
headers=headers,
|
||
)
|
||
# 若响应错误代码非0则抛出异常
|
||
if response["code"] != 0:
|
||
raise RuntimeError(
|
||
f"请求多维表格查询记录失败：{response['code']} {response['message']}"
|
||
)
|
||
|
||
# 合并多维表格记录
|
||
records.extend(response["data"]["items"])
|
||
|
||
# 若响应没有更多记录则跳出循环
|
||
if not response["data"]["has_more"]:
|
||
break
|
||
|
||
# 更新分页标识
|
||
page_token = response["data"]["page_token"]
|
||
|
||
return records
|
||
|
||
def _convert_to_cloudreve_direct_link(self, material_token: str) -> str:
|
||
"""
|
||
转为Cloudreve直链
|
||
:param material_token: 素材标识
|
||
:return: 素材直链地址
|
||
"""
|
||
# 获取 Cloudreve 上传 session_id
|
||
session_id = self.http_client.
|
||
|
||
|
||
|
||
|
||
# 构建下载素材的请求地址
|
||
url = f"https://open.feishu.cn/open-apis/drive/v1/medias/{material_token}/download" # https://open.feishu.cn/document/server-docs/docs/drive-v1/media/download
|
||
|
||
headers = self._get_headers()
|
||
# 添加 Content-Type 请求头
|
||
headers.update(
|
||
{
|
||
"Content-Type": "application/json; charset=utf-8",
|
||
}
|
||
)
|
||
|
||
response = self.http_client.download(
|
||
url=url,
|
||
headers=headers,
|
||
<<<<<<< HEAD
|
||
stream_enabled=True,
|
||
) # 默认使用流式传输
|
||
|
||
=======
|
||
stream_enabled=stream_enabled,
|
||
)
|
||
print(type(response[0]))
|
||
print(type(response[1]))
|
||
print(type(response[2]))
|
||
|
||
>>>>>>> 239b7d7f2837822ce7a85afdcb85bafc4888d6f7
|
||
|
||
|
||
a = Feishu()
|
||
|
||
print(
|
||
a.download_material(
|
||
file_token="DsG4bY3iKo0n6Bx6O5fcKAbnnCh",
|
||
)
|
||
)
|