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
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
| import asyncio
import aiohttp
import json
import html
import re
from pathlib import Path
from typing import List, Dict, Any
class BilibiliFetcher:
def __init__(self):
# 注意：请将下面的Cookie替换为您自己的真实Cookie
self.headers = {
'Cookie': 'SESSDATA=你的SESSDATA内容',
'Origin': 'https://www.bilibili.com',
'Referer': 'https://www.bilibili.com/',
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/123.0.0.0 Safari/537.36'
}
self.session = None
self.uid = None
def encode_html(self, text: str) -> str:
"""HTML编码函数，与JavaScript版本保持一致"""
if not isinstance(text, str):
return ''
# 基本HTML实体编码
text = text.replace('&', '&')
text = text.replace('<', '<')
text = text.replace('>', '>')
text = text.replace('"', '"')
# 处理空格：连续空格、行首行尾空格转换为
text = re.sub(r' (?= )|(?<= ) |^ | $', ' ', text, flags=re.MULTILINE)
# 换行符转换为<br />
text = re.sub(r'\r\n|\r|\n', '<br />', text)
return text
async def create_session(self):
"""创建aiohttp会话"""
self.session = aiohttp.ClientSession(headers=self.headers)
async def close_session(self):
"""关闭aiohttp会话"""
if self.session:
await self.session.close()
async def get_user_info(self) -> int:
"""获取自己的UID"""
try:
async with self.session.get('https://api.bilibili.com/x/web-interface/nav') as response:
ujson = await response.json()
if ujson['code'] != 0:
print(f'获取用户信息失败: {ujson["message"]}')
raise Exception(f'获取用户信息失败: {ujson["message"]}')
self.uid = ujson['data']['mid']
return self.uid
except Exception as e:
print(f'获取用户信息时出错: {str(e)}')
raise
async def get_followers_page(self, page: int) -> List[Dict[str, Any]]:
"""获取指定页的粉丝信息"""
try:
url = f'https://api.bilibili.com/x/relation/fans?vmid={self.uid}&ps=50&pn={page}'
async with self.session.get(url) as response:
data = await response.json()
if data['code'] == 0 and data.get('data') and data['data'].get('list'):
return data['data']['list']
else:
print(f'获取第{page}页粉丝信息失败: {data.get("message", "未知错误")}')
return []
except Exception as e:
print(f'请求第{page}页时出错: {str(e)}')
return []
async def get_all_followers(self, max_pages: int = 20) -> List[Dict[str, Any]]:
"""获取所有粉丝信息"""
followers = []
# 获取前20页粉丝的信息，每页50个
for i in range(1, max_pages + 1):
page_followers = await self.get_followers_page(i)
if not page_followers:
break
followers.extend(page_followers)
return followers
async def get_followers_detail_info(self, followers: List[Dict[str, Any]]) -> None:
"""获取所有粉丝的详细信息"""
if not followers:
return
uids = [str(f['mid']) for f in followers]
uid_str = ','.join(uids)
try:
url = f'https://api.vc.bilibili.com/x/im/user_infos?uids={uid_str}'
async with self.session.get(url) as response:
cjson = await response.json()
if cjson['code'] == 0 and cjson.get('data'):
# 将详细信息合并到粉丝对象中
for info in cjson['data']:
follower = next((f for f in followers if f['mid'] == info['mid']), None)
if follower:
follower.update(info)
except Exception as e:
print(f'获取粉丝详细信息时出错: {str(e)}')
async def get_followers_stats(self, followers: List[Dict[str, Any]]) -> None:
"""获取所有粉丝的粉丝数统计"""
if not followers:
return
# 分批处理，每批最多20个
followers_without_stat = [f['mid'] for f in followers]
while followers_without_stat:
batch = followers_without_stat[:20]
followers_without_stat = followers_without_stat[20:]
try:
mids_str = ','.join(map(str, batch))
url = f'https://api.bilibili.com/x/relation/stats?mids={mids_str}'
async with self.session.get(url) as response:
sjson = await response.json()
if sjson['code'] == 0 and sjson.get('data'):
# 将统计信息合并到粉丝对象中
for mid_str, stat in sjson['data'].items():
mid = int(mid_str)
follower = next((f for f in followers if f['mid'] == mid), None)
if follower:
follower.update(stat)
except Exception as e:
print(f'获取粉丝统计信息时出错: {str(e)}')
def filter_default_avatars(self, followers: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
"""过滤掉使用默认头像的用户"""
filtered = [f for f in followers if '/member/noface.jpg' not in f.get('face', '')]
print(f'原始粉丝数量: {len(followers)}')
print(f'过滤后粉丝数量: {len(filtered)}')
print(f'已过滤掉 {len(followers) - len(filtered)} 个默认头像用户')
return filtered
def generate_html(self, followers: List[Dict[str, Any]], output_file: str = 'followers.html') -> None:
"""生成HTML文件"""
content = f'''<!DOCTYPE html>
<html lang="zh-CN">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>粉丝列表</title>
<style>
* {{
font-family: Lato, 'PingFang SC', 'Microsoft YaHei', sans-serif;
font-size: 20px;
overflow-wrap: anywhere;
text-align: justify;
margin: 0;
padding: 0;
box-sizing: border-box;
}}
body {{
background: #f5f7fa;
padding: 20px;
line-height: 1.6;
min-height: 100vh;
}}
.container {{
width: 100%;
max-width: none;
}}
.header {{
text-align: center;
margin-bottom: 30px;
}}
.header h1 {{
font-size: 32px;
font-weight: 600;
color: #1f2937;
margin-bottom: 8px;
}}
.header p {{
font-size: 16px;
color: #6b7280;
}}
.followers-content {{
background: white;
border-radius: 12px;
padding: 20px;
box-shadow: 0 4px 6px rgba(0, 0, 0, 0.05);
width: 100%;
}}
div.inline-block {{
display: inline-block;
margin-right: 5px;
margin-bottom: 10px;
}}
div.info {{
align-items: center;
display: flex;
}}
div.image-wrap {{
margin-right: 5px;
position: relative;
}}
img {{
vertical-align: middle;
}}
img.face {{
border-radius: 50%;
height: 60px;
}}
img.icon-face-nft {{
border: 2px solid var(--background-color);
box-sizing: border-box;
}}
div.image-wrap.has-frame img.face {{
height: 51px;
padding: 19.5px;
}}
div.image-wrap.has-frame img.face-frame {{
height: 90px;
left: calc(50% - 45px);
position: absolute;
top: 0;
}}
div.image-wrap img.face-icon {{
border-radius: 50%;
height: 18px;
left: calc(50% + 13.25px);
position: absolute;
top: calc(50% + 13.25px);
}}
div.image-wrap img.face-icon.second {{
left: calc(50% - 3.75px);
}}
div.image-wrap.has-frame img.face-icon {{
left: calc(50% + 9px);
top: calc(50% + 9px);
}}
div.image-wrap.has-frame img.face-icon.second {{
left: calc(50% - 8px);
}}
@media (max-width: 768px) {{
body {{
padding: 10px;
}}
.header h1 {{
font-size: 24px;
}}
.followers-content {{
padding: 15px;
}}
* {{
font-size: 18px;
}}
img.face {{
height: 50px;
}}
}}
@media (max-width: 480px) {{
body {{
padding: 5px;
}}
.followers-content {{
padding: 10px;
}}
* {{
font-size: 16px;
}}
img.face {{
height: 40px;
}}
}}
</style>
</head>
<body>
<div class="container">
<div class="header">
<h1>粉丝列表</h1>
<p>共 {len(followers)} 位粉丝（已过滤默认头像用户）</p>
</div>
<div class="followers-content">
{''.join([f'<div class="inline-block"><div class="info"><div class="image-wrap"><img class="face" src="{f.get("face", "")}" referrerpolicy="no-referrer" /></div> <div><strong>{self.encode_html(f.get("name") or f.get("uname", ""))}</strong></div></div></div>' for f in followers])}
</div>
</div>
</body>
</html>'''
# 写入文件
with open(output_file, 'w', encoding='utf-8') as f:
f.write(content)
print(f'成功生成粉丝列表HTML文件，共包含 {len(followers)} 个粉丝')
async def main():
"""主函数"""
fetcher = BilibiliFetcher()
try:
# 创建会话
await fetcher.create_session()
# 获取用户UID
await fetcher.get_user_info()
# 获取所有粉丝信息
followers = await fetcher.get_all_followers(max_pages=20)
# 获取所有粉丝的详细信息
await fetcher.get_followers_detail_info(followers)
# 获取所有粉丝的粉丝数
await fetcher.get_followers_stats(followers)
# 过滤掉使用默认头像的用户
filtered_followers = fetcher.filter_default_avatars(followers)
# 生成HTML文件
fetcher.generate_html(filtered_followers, 'followers.html')
except Exception as e:
print(f'程序运行出错: {str(e)}')
return 1
finally:
# 关闭会话
await fetcher.close_session()
return 0
if __name__ == "__main__":
try:
exit_code = asyncio.run(main())
exit(exit_code)
except KeyboardInterrupt:
print("\n程序被用户中断")
exit(1)
except Exception as error:
print(f'程序运行出错: {str(error)}')
exit(1)
|