fix: consider image data-src and make generated alt text optional (#50)

* fix: image src and alt

* fix

* docs: doc about x-with-generated-alt

* fix: deps

README.md

@@ -72,6 +72,7 @@ As you have already seen above, one can control the behavior of the Reader API u
   - `x-respond-with: screenshot` returns the URL of the webpage's screenshot
 - You can specify a proxy server via the `x-proxy-url` header.
 - You can bypass the cached page (lifetime 300s) via the `x-no-cache` header.
+- You can enable alt-text generation feature via the `x-with-generated-alt` header.
 
 ### JSON mode (super early beta)
 

backend/functions/src/cloud-functions/crawler.ts

@@ -5,7 +5,7 @@ import {
     AssertionFailureError, ParamValidationError,
 } from 'civkit';
 import { singleton } from 'tsyringe';
-import { CloudHTTPv2, Ctx, FirebaseStorageBucketControl, InsufficientBalanceError, Logger, OutputServerEventStream, RPCReflect } from '../shared';
+import { AsyncContext, CloudHTTPv2, Ctx, FirebaseStorageBucketControl, InsufficientBalanceError, Logger, OutputServerEventStream, RPCReflect } from '../shared';
 import { RateLimitControl } from '../shared/services/rate-limit';
 import _ from 'lodash';
 import { PageSnapshot, PuppeteerControl, ScrappingOptions } from '../services/puppeteer';
@@ -41,6 +41,7 @@ export class CrawlerHost extends RPCHost {
         protected altTextService: AltTextService,
         protected firebaseObjectStorage: FirebaseStorageBucketControl,
         protected rateLimitControl: RateLimitControl,
+        protected threadLocal: AsyncContext,
     ) {
         super(...arguments);
 
@@ -123,8 +124,8 @@ export class CrawlerHost extends RPCHost {
             turnDownService = turnDownService.use(plugin);
         }
         const urlToAltMap: { [k: string]: string | undefined; } = {};
-        if (snapshot.imgs?.length) {
-            const tasks = (snapshot.imgs || []).map(async (x) => {
+        if (snapshot.imgs?.length && this.threadLocal.get('withGeneratedAlt')) {
+            const tasks = _.uniqBy((snapshot.imgs || []), 'src').map(async (x) => {
                 const r = await this.altTextService.getAltText(x).catch((err: any) => {
                     this.logger.warn(`Failed to get alt text for ${x.src}`, { err: marshalErrorLike(err) });
                     return undefined;
@@ -140,7 +141,15 @@ export class CrawlerHost extends RPCHost {
         turnDownService.addRule('img-generated-alt', {
             filter: 'img',
             replacement: (_content, node) => {
-                const src = (node.getAttribute('src') || '').trim();
+                let linkPreferredSrc = (node.getAttribute('src') || '').trim();
+                if (!linkPreferredSrc || linkPreferredSrc.startsWith('data:')) {
+                    const dataSrc = (node.getAttribute('data-src') || '').trim();
+                    if (dataSrc && !dataSrc.startsWith('data:')) {
+                        linkPreferredSrc = dataSrc;
+                    }
+                }
+
+                const src = linkPreferredSrc;
                 const alt = cleanAttribute(node.getAttribute('alt'));
                 if (!src) {
                     return '';
@@ -285,6 +294,11 @@ ${this.content}
                         in: 'header',
                         schema: { type: 'string' }
                     },
+                    'X-With-Generated-Alt': {
+                        description: `Enable automatic alt-text generating for images without an meaningful alt-text.`,
+                        in: 'header',
+                        schema: { type: 'string' }
+                    },
                 }
             }
         },
@@ -365,6 +379,7 @@ ${authMixin}`,
         }
 
         const customMode = ctx.req.get('x-respond-with') || 'default';
+        const withGeneratedAlt = Boolean(ctx.req.get('x-with-generated-alt'));
         const noCache = Boolean(ctx.req.get('x-no-cache'));
         const cookies: CookieParam[] = [];
         const setCookieHeaders = ctx.req.headers['x-set-cookie'];
@@ -381,6 +396,7 @@ ${authMixin}`,
                 domain: urlToCrawl.hostname,
             });
         }
+        this.threadLocal.set('withGeneratedAlt', withGeneratedAlt);
 
         const crawlOpts: ScrappingOptions = {
             proxyUrl: ctx.req.get('x-proxy-url'),

backend/functions/src/services/alt-text.ts

@@ -12,6 +12,7 @@ const md5Hasher = new HashManager('md5', 'hex');
 @singleton()
 export class AltTextService extends AsyncService {
 
+    altsToIgnore = 'image,img,photo,picture,pic,alt,figure,fig'.split(',');
     logger = this.globalLogger.child({ service: this.constructor.name });
 
     constructor(
@@ -48,7 +49,7 @@ export class AltTextService extends AsyncService {
         if (!imgBrief.src) {
             return undefined;
         }
-        if (imgBrief.alt) {
+        if (imgBrief.alt && !this.altsToIgnore.includes(imgBrief.alt.trim().toLowerCase())) {
             return imgBrief.alt;
         }
         const digest = md5Hasher.hash(imgBrief.src);

backend/functions/src/services/puppeteer.ts

@@ -193,17 +193,26 @@ export class PuppeteerControl extends AsyncService {
         preparations.push(page.evaluateOnNewDocument(READABILITY_JS));
         preparations.push(page.evaluateOnNewDocument(`
 function briefImgs(elem) {
-    const imageTags = Array.from((elem || document).querySelectorAll('img[src]'));
-
-    return imageTags.map((x)=> ({
-        src: x.src,
-        loaded: x.complete,
-        width: x.width,
-        height: x.height,
-        naturalWidth: x.naturalWidth,
-        naturalHeight: x.naturalHeight,
-        alt: x.alt || x.title,
-    }));
+    const imageTags = Array.from((elem || document).querySelectorAll('img[src],img[data-src]'));
+
+    return imageTags.map((x)=> {
+        let linkPreferredSrc = x.src;
+        if (linkPreferredSrc.startsWith('data:')) {
+            if (typeof x.dataset?.src === 'string' && !x.dataset.src.startsWith('data:')) {
+                linkPreferredSrc = x.dataset.src;
+            }
+        }
+
+        return {
+            src: linkPreferredSrc,
+            loaded: x.complete,
+            width: x.width,
+            height: x.height,
+            naturalWidth: x.naturalWidth,
+            naturalHeight: x.naturalHeight,
+            alt: x.alt || x.title,
+        };
+    });
 }
 function giveSnapshot() {
     let parsed;