1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
|
from ATRI.service import Service
from ATRI.rule import is_in_service
from ATRI.database.db import DB
from ATRI.utils import timestamp2datetime
import json
import aiohttp
import os
import re
import asyncio
from typing import Any
from operator import itemgetter
__doc__ = """b站订阅动态助手
"""
__session_pool = {}
def get_api(field: str):
"""
获取 API。
Args:
field (str): API 所属分类,即 data/api 下的文件名(不含后缀名)
Returns:
dict, 该 API 的内容。
"""
path = os.path.abspath(
os.path.join(os.path.dirname(__file__), f"{field.lower()}.json")
)
if os.path.exists(path):
with open(path, encoding="utf8") as f:
return json.loads(f.read())
API = get_api("user")
def get_session():
"""
获取当前模块的 aiohttp.ClientSession 对象,用于自定义请求
Returns:
aiohttp.ClientSession
"""
loop = asyncio.get_event_loop()
session = __session_pool.get(loop, None)
if session is None:
session = aiohttp.ClientSession(loop=loop)
__session_pool[loop] = session
return session
async def bilibili_request(
method: str,
url: str,
params: dict = None,
data: Any = None,
no_csrf: bool = False,
json_body: bool = False,
**kwargs,
):
"""
向接口发送请求。
Args:
method (str) : 请求方法。
url (str) : 请求 URL。
params (dict, optional) : 请求参数。
data (Any, optional) : 请求载荷。
no_csrf (bool, optional) : 不要自动添加 CSRF。
json_body (bool, optional) 载荷是否为 JSON
Returns:
接口未返回数据时,返回 None,否则返回该接口提供的 data 或 result 字段的数据。
"""
method = method.upper()
# 使用 Referer 和 UA 请求头以绕过反爬虫机制
DEFAULT_HEADERS = {
"Referer": "https://www.bilibili.com",
"User-Agent": "Mozilla/5.0",
}
headers = DEFAULT_HEADERS
if params is None:
params = {}
# 自动添加 csrf
if not no_csrf and method in ["POST", "DELETE", "PATCH"]:
if data is None:
data = {}
data["csrf"] = ""
data["csrf_token"] = ""
# jsonp
if params.get("jsonp", "") == "jsonp":
params["callback"] = "callback"
config = {
"method": method,
"url": url,
"params": params,
"data": data,
"headers": headers,
"cookies": "",
}
config.update(kwargs)
if json_body:
config["headers"]["Content-Type"] = "application/json"
config["data"] = json.dumps(config["data"])
session = get_session()
async with session.request(**config) as resp:
# 检查状态码
try:
resp.raise_for_status()
except aiohttp.ClientResponseError as e:
raise Exception(e.message)
# 检查响应头 Content-Length
content_length = resp.headers.get("content-length")
if content_length and int(content_length) == 0:
return None
# 检查响应头 Content-Type
content_type = resp.headers.get("content-type")
# 不是 application/json
if content_type.lower().index("application/json") == -1:
raise Exception("响应不是 application/json 类型")
raw_data = await resp.text()
resp_data: dict
if "callback" in params:
# JSONP 请求
resp_data = json.loads(re.match("^.*?({.*}).*$", raw_data, re.S).group(1))
else:
# JSON
resp_data = json.loads(raw_data)
# 检查 code
code = resp_data.get("code", None)
if code is None:
raise Exception("API 返回数据未含 code 字段")
if code != 0:
msg = resp_data.get("msg", None)
if msg is None:
msg = resp_data.get("message", None)
if msg is None:
msg = "接口未返回错误信息"
raise Exception(msg)
real_data = resp_data.get("data", None)
if real_data is None:
real_data = resp_data.get("result", None)
return real_data
class User:
"""
b站用户相关
"""
def __init__(self, uid: int):
"""
Args:
uid (int) : 用户 UID
"""
self.uid = uid
self.__self_info = None
async def get_user_info(self):
"""
获取用户信息(昵称,性别,生日,签名,头像 URL,空间横幅 URL 等)
Returns:
dict: 调用接口返回的内容。
"""
api = API["info"]["info"]
params = {"mid": self.uid}
return await bilibili_request("GET", url=api["url"], params=params)
async def get_dynamics(self, offset: int = 0, need_top: bool = False):
"""
获取用户动态。
Args:
offset (str, optional): 该值为第一次调用本方法时,数据中会有个 next_offset 字段,
指向下一动态列表第一条动态(类似单向链表)。
根据上一次获取结果中的 next_offset 字段值,
循环填充该值即可获取到全部动态。
0 为从头开始。
Defaults to 0.
need_top (bool, optional): 显示置顶动态. Defaults to False.
Returns:
dict: 调用接口返回的内容。
"""
api = API["info"]["dynamic"]
params = {
"host_uid": self.uid,
"offset_dynamic_id": offset,
"need_top": 1 if need_top else 0,
}
data = await bilibili_request("GET", url=api["url"], params=params)
# card 字段自动转换成 JSON。
if "cards" in data:
for card in data["cards"]:
card["card"] = json.loads(card["card"])
card["extend_json"] = json.loads(card["extend_json"])
return data
class BilibiliDynamicSubscriptor(Service):
def __init__(self):
Service.__init__(self, "b站动态订阅", __doc__, rule=is_in_service("b站动态订阅"))
async def add_subscription(self, uid: int, groupid: int) -> bool:
async with DB() as db:
res = await db.add_subscription(uid=uid, groupid=groupid)
return res
async def remove_subscription(self, uid: int, groupid: int) -> bool:
async with DB() as db:
res = await db.remove_subscription(
query_map={"uid": uid, "groupid": groupid}
)
return res
async def get_subscriptions(self, query_map: dict) -> list:
async with DB() as db:
res = await db.get_subscriptions(query_map=query_map)
return res
async def update_subscription_by_uid(self, uid: int, update_map: dict) -> bool:
async with DB() as db:
res = await db.update_subscriptions_by_uid(uid=uid, update_map=update_map)
return res
async def get_all_subscriptions(self) -> list:
async with DB() as db:
res = await db.get_all_subscriptions()
return res
# bilibili network function
async def get_upname_by_uid(self, uid: int) -> str:
try:
u = User(uid)
info = await u.get_user_info()
return info.get("name")
except:
return ""
async def get_recent_dynamic_by_uid(self, uid: int) -> dict:
try:
u = User(uid)
info = await u.get_dynamics()
return info
except:
return {}
def extract_dynamics_detail(self, dynamic_list: list) -> list:
import time
ret = []
for d in dynamic_list:
pattern = {}
desc = d["desc"]
card = d["card"]
type = desc["type"]
# common 部分
pattern["type"] = desc["type"]
pattern["uid"] = desc["uid"]
pattern["view"] = desc["view"]
pattern["repost"] = desc["repost"]
pattern["like"] = desc["like"]
pattern["dynamic_id"] = desc["dynamic_id"]
pattern["timestamp"] = desc["timestamp"]
pattern["time"] = timestamp2datetime(desc["timestamp"])
pattern["type_zh"] = ""
# alternative 部分
pattern["content"] = ""
pattern["pic"] = ""
# 根据type区分 提取content
if type == 1: # 转发动态
pattern["type_zh"] = "转发动态"
pattern["content"] = card["item"]["content"]
pattern["pic"] = card["user"]["face"]
elif type == 2: # 普通动态(带多张图片)
pattern["type_zh"] = "普通动态(附图)"
pattern["content"] = card["item"]["description"]
if card["item"]["pictures_count"] > 0:
if isinstance(card["item"]["pictures"][0], str):
pattern["pic"] = card["item"]["pictures"][0]
else:
pattern["pic"] = card["item"]["pictures"][0]["img_src"]
elif type == 4: # 普通动态(纯文字)
pattern["type_zh"] = "普通动态(纯文字)"
pattern["content"] = card["item"]["content"]
# 无图片
elif type == 8: # 视频动态
pattern["type_zh"] = "视频动态"
pattern["content"] = card["title"] + card["dynamic"]
pattern["pic"] = card["pic"]
elif type == 64: # 文章
pattern["type_zh"] = "文章"
pattern["content"] = card["title"] + card["summary"]
if len(card["image_urls"]) > 0:
pattern["pic"] = card["image_urls"][0]
ret.append(pattern)
ret = sorted(ret, key=itemgetter("timestamp"))
return ret
def generate_output(self, pattern: dict) -> (str, str):
# 限制摘要的字数
abstractLimit = 40
text_part = """【UP名称】{name}\n【动态类型】{dynamic_type}\n【时间】{time}\n【内容摘要】{content}\n""".format(
name=pattern["name"],
dynamic_type=pattern["type_zh"],
time=pattern["time"],
content=pattern["content"][:abstractLimit],
)
pic_part = pattern["pic"]
return text_part, pic_part
|