this repo has no description
feat: Enhance link handling to support processing of forwarded messages and multiple links
+231
-55
+12
README.md
+12
README.md
···
5
5
## Features
6
6
7
7
- Extract images from various supported websites
8
+
- Process forwarded messages containing links (including button links)
8
9
- Queue images for scheduled posting
9
10
- Customizable posting schedule using cron syntax
10
11
- Access control to limit who can use the bot
···
270
271
271
272
### Adding Images to Queue
272
273
274
+
#### Direct Links
273
275
Send a link from any supported website to the bot in a direct message. The bot will extract the image and add it to the queue.
276
+
277
+
#### Forwarded Messages
278
+
The bot can also process forwarded messages that contain links to supported websites. This includes:
279
+
280
+
- **Text Links**: Any URLs found in the forwarded message text will be extracted and processed
281
+
- **Button Links**: URLs embedded in inline keyboard buttons (common in channel posts) are automatically detected and processed
282
+
- **Multiple Links**: If a forwarded message contains multiple valid links, all will be processed simultaneously
283
+
- **Error Handling**: Invalid links are silently discarded - the bot will only show an error if zero valid links are found
284
+
285
+
**Usage**: Simply forward any message containing supported website links to the bot. The bot will automatically detect it's a forwarded message and extract all valid URLs for processing.
274
286
275
287
### Interactive Queue Management
276
288
+1
bot/telegrambot/commands/help.js
+1
bot/telegrambot/commands/help.js
···
24
24
/update - Update bot from GitHub repository (owner only)
25
25
26
26
Send any link to a supported site to add it to the queue.
27
+
Forward messages with links or buttons to extract and queue multiple items.
27
28
Supported sites: e621, FurAffinity, SoFurry, Weasyl, Bluesky
28
29
`;
29
30
this.bot.sendMessage(chatId, helpText);
+174
-50
bot/telegrambot/commands/linkHandler.js
+174
-50
bot/telegrambot/commands/linkHandler.js
···
14
14
15
15
register() {
16
16
this.bot.on('message', async (msg) => {
17
+
// Check for direct URL messages
17
18
if (msg.text && msg.text.startsWith('http')) {
18
-
const chatId = msg.chat.id;
19
-
20
-
// Skip processing if this is part of an announcement setup
21
-
const isInAnnouncementFlow = this.pendingAnnouncements && this.pendingAnnouncements[msg.from.id];
22
-
const isInButtonEditFlow = this.editingAnnouncementButton && this.editingAnnouncementButton[msg.from.id];
23
-
24
-
if (isInAnnouncementFlow || isInButtonEditFlow) {
25
-
// This URL is part of an announcement setup, so we should not process it as a link
26
-
return;
27
-
}
28
-
29
-
if (!this.authHelper.isAuthorized(msg.from.id)) {
30
-
this.bot.sendMessage(chatId, 'You are not authorized to use this bot.');
31
-
return;
32
-
}
33
-
34
-
try {
35
-
const url = msg.text.trim();
36
-
37
-
this.bot.sendMessage(chatId, 'Processing link...', { reply_to_message_id: msg.message_id });
38
-
39
-
const mediaData = await scraperManager.extractFromUrl(url);
40
-
41
-
// Check if the scraper returned an error (for temporarily disabled scrapers)
42
-
if (mediaData.error) {
43
-
this.bot.sendMessage(
44
-
chatId,
45
-
mediaData.error,
46
-
{ reply_to_message_id: msg.message_id }
47
-
);
48
-
return;
49
-
}
50
-
51
-
await queueManager.addToQueue(mediaData);
52
-
53
-
const queueLength = await queueManager.getQueueLength();
54
-
const mediaType = mediaData.isVideo ? 'Video' : 'Image';
55
-
56
-
this.bot.sendMessage(
57
-
chatId,
58
-
`Added to queue: ${mediaType} - ${mediaData.title}\nCurrent queue length: ${queueLength}`,
59
-
{ reply_to_message_id: msg.message_id }
60
-
);
61
-
} catch (error) {
62
-
this.bot.sendMessage(
63
-
chatId,
64
-
`Error processing link: ${error.message}`,
65
-
{ reply_to_message_id: msg.message_id }
66
-
);
67
-
}
19
+
await this.processDirectUrl(msg);
20
+
return;
21
+
}
22
+
23
+
// Check for forwarded messages
24
+
if (msg.forward_from || msg.forward_from_chat) {
25
+
await this.processForwardedMessage(msg);
26
+
return;
68
27
}
69
28
});
29
+
}
30
+
31
+
/**
32
+
* Process a direct URL message
33
+
*/
34
+
async processDirectUrl(msg) {
35
+
const chatId = msg.chat.id;
36
+
37
+
// Skip processing if this is part of an announcement setup
38
+
const isInAnnouncementFlow = this.pendingAnnouncements && this.pendingAnnouncements[msg.from.id];
39
+
const isInButtonEditFlow = this.editingAnnouncementButton && this.editingAnnouncementButton[msg.from.id];
40
+
41
+
if (isInAnnouncementFlow || isInButtonEditFlow) {
42
+
// This URL is part of an announcement setup, so we should not process it as a link
43
+
return;
44
+
}
45
+
46
+
if (!this.authHelper.isAuthorized(msg.from.id)) {
47
+
this.bot.sendMessage(chatId, 'You are not authorized to use this bot.');
48
+
return;
49
+
}
50
+
51
+
try {
52
+
const url = msg.text.trim();
53
+
54
+
this.bot.sendMessage(chatId, 'Processing link...', { reply_to_message_id: msg.message_id });
55
+
56
+
const mediaData = await scraperManager.extractFromUrl(url);
57
+
58
+
// Check if the scraper returned an error (for temporarily disabled scrapers)
59
+
if (mediaData.error) {
60
+
this.bot.sendMessage(
61
+
chatId,
62
+
mediaData.error,
63
+
{ reply_to_message_id: msg.message_id }
64
+
);
65
+
return;
66
+
}
67
+
68
+
await queueManager.addToQueue(mediaData);
69
+
70
+
const queueLength = await queueManager.getQueueLength();
71
+
const mediaType = mediaData.isVideo ? 'Video' : 'Image';
72
+
73
+
this.bot.sendMessage(
74
+
chatId,
75
+
`Added to queue: ${mediaType} - ${mediaData.title}\nCurrent queue length: ${queueLength}`,
76
+
{ reply_to_message_id: msg.message_id }
77
+
);
78
+
} catch (error) {
79
+
this.bot.sendMessage(
80
+
chatId,
81
+
`Error processing link: ${error.message}`,
82
+
{ reply_to_message_id: msg.message_id }
83
+
);
84
+
}
85
+
}
86
+
87
+
/**
88
+
* Process a forwarded message that may contain links in text or buttons
89
+
*/
90
+
async processForwardedMessage(msg) {
91
+
const chatId = msg.chat.id;
92
+
93
+
if (!this.authHelper.isAuthorized(msg.from.id)) {
94
+
this.bot.sendMessage(chatId, 'You are not authorized to use this bot.');
95
+
return;
96
+
}
97
+
98
+
// Extract URLs from the forwarded message
99
+
const urls = this.extractUrlsFromMessage(msg);
100
+
101
+
if (urls.length === 0) {
102
+
// No URLs found - silently ignore
103
+
return;
104
+
}
105
+
106
+
try {
107
+
this.bot.sendMessage(chatId, `Processing forwarded message with ${urls.length} link(s)...`, { reply_to_message_id: msg.message_id });
108
+
109
+
const results = await scraperManager.extractFromUrls(urls);
110
+
111
+
if (results.validResults.length === 0) {
112
+
this.bot.sendMessage(
113
+
chatId,
114
+
'❌ No valid links found in the forwarded message.',
115
+
{ reply_to_message_id: msg.message_id }
116
+
);
117
+
return;
118
+
}
119
+
120
+
// Add all valid results to queue
121
+
for (const mediaData of results.validResults) {
122
+
await queueManager.addToQueue(mediaData);
123
+
}
124
+
125
+
const queueLength = await queueManager.getQueueLength();
126
+
let responseMessage = `✅ Added ${results.validResults.length} item(s) to queue`;
127
+
128
+
if (results.invalidUrls.length > 0) {
129
+
responseMessage += ` (${results.invalidUrls.length} invalid link(s) silently discarded)`;
130
+
}
131
+
132
+
responseMessage += `\nCurrent queue length: ${queueLength}`;
133
+
134
+
this.bot.sendMessage(
135
+
chatId,
136
+
responseMessage,
137
+
{ reply_to_message_id: msg.message_id }
138
+
);
139
+
} catch (error) {
140
+
this.bot.sendMessage(
141
+
chatId,
142
+
`Error processing forwarded message: ${error.message}`,
143
+
{ reply_to_message_id: msg.message_id }
144
+
);
145
+
}
146
+
}
147
+
148
+
/**
149
+
* Extract URLs from a message's text and inline keyboard buttons
150
+
*/
151
+
extractUrlsFromMessage(msg) {
152
+
const urls = [];
153
+
154
+
// Extract URLs from message text
155
+
if (msg.text) {
156
+
const textUrls = this.extractUrlsFromText(msg.text);
157
+
urls.push(...textUrls);
158
+
}
159
+
160
+
// Extract URLs from inline keyboard buttons
161
+
if (msg.reply_markup && msg.reply_markup.inline_keyboard) {
162
+
const buttonUrls = this.extractUrlsFromInlineKeyboard(msg.reply_markup.inline_keyboard);
163
+
urls.push(...buttonUrls);
164
+
}
165
+
166
+
// Remove duplicates
167
+
return [...new Set(urls)];
168
+
}
169
+
170
+
/**
171
+
* Extract URLs from text using regex
172
+
*/
173
+
extractUrlsFromText(text) {
174
+
const urlRegex = /https?:\/\/[^\s]+/g;
175
+
const matches = text.match(urlRegex);
176
+
return matches || [];
177
+
}
178
+
179
+
/**
180
+
* Extract URLs from inline keyboard buttons
181
+
*/
182
+
extractUrlsFromInlineKeyboard(inlineKeyboard) {
183
+
const urls = [];
184
+
185
+
for (const row of inlineKeyboard) {
186
+
for (const button of row) {
187
+
if (button.url) {
188
+
urls.push(button.url);
189
+
}
190
+
}
191
+
}
192
+
193
+
return urls;
70
194
}
71
195
72
196
// Allow other modules to set these properties for proper URL handling during announcements
+5
-5
queue/alert-state.json
+5
-5
queue/alert-state.json
···
1
1
{
2
-
"lowQueueAlertSent": false,
3
-
"emptyQueueAlertSent": false,
4
-
"lastLowQueueAlertTime": 1748136883217,
5
-
"lastEmptyQueueAlertTime": 1748136540595,
6
-
"lastSaved": 1749076222424
2
+
"lowQueueAlertSent": true,
3
+
"emptyQueueAlertSent": true,
4
+
"lastLowQueueAlertTime": 1749155645693,
5
+
"lastEmptyQueueAlertTime": 1749155676860,
6
+
"lastSaved": 1749155688499
7
7
}
+39
utils/scraperManager.js
+39
utils/scraperManager.js
···
38
38
39
39
return await scraper.extract(url);
40
40
}
41
+
42
+
/**
43
+
* Extract image data from multiple URLs, handling failures gracefully
44
+
* @param {string[]} urls - Array of URLs to extract from
45
+
* @returns {Promise<{validResults: Array, invalidUrls: string[]}>} - Results with valid extractions and invalid URLs
46
+
*/
47
+
async extractFromUrls(urls) {
48
+
const validResults = [];
49
+
const invalidUrls = [];
50
+
51
+
for (const url of urls) {
52
+
try {
53
+
const scraper = this.findScraper(url);
54
+
55
+
if (!scraper) {
56
+
invalidUrls.push(url);
57
+
continue;
58
+
}
59
+
60
+
const mediaData = await scraper.extract(url);
61
+
62
+
// Check if the scraper returned an error (for temporarily disabled scrapers)
63
+
if (mediaData.error) {
64
+
invalidUrls.push(url);
65
+
continue;
66
+
}
67
+
68
+
validResults.push(mediaData);
69
+
} catch (error) {
70
+
// Silently add to invalid URLs list
71
+
invalidUrls.push(url);
72
+
}
73
+
}
74
+
75
+
return {
76
+
validResults,
77
+
invalidUrls
78
+
};
79
+
}
41
80
}
42
81
43
82
module.exports = new ScraperManager();