Skip to content

refactor: drop node-pdf-parser for local parser #38

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
battlesquid merged 2 commits into from
May 16, 2026
Merged

refactor: drop node-pdf-parser for local parser #38

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2519966
refactor: drop node-pdf-parser for local parser
battlesquid May 16, 2026
34b7298
chore: neat
battlesquid May 16, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion packages/scraper-strategies/package.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
{
"name": "@qnaplus/scraper-strategies",
"version": "3.1.3",
"version": "3.1.4",
"description": "Request stategies for @qnaplus/scraper",
"main": "dist/index.js",
"repository": {
Expand Down
4 changes: 2 additions & 2 deletions packages/scraper/package.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
{
"name": "@qnaplus/scraper",
"version": "3.1.3",
"version": "3.1.4",
"description": "Utility package to scrape questions from the VEX Robotics Q&A.",
"main": "dist/index.js",
"repository": {
Expand All @@ -23,7 +23,7 @@
"@crawlee/core": "^3.16.0",
"cheerio": "^1.2.0",
"got-scraping": "^4.2.1",
"node-pdf-parser": "^1.0.7",
"pdfjs-dist": "^5.7.284",
"pino": "catalog:"
},
"devDependencies": {
Expand Down
23 changes: 20 additions & 3 deletions packages/scraper/src/modules/rules.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,3 @@
import { parsepdf } from "node-pdf-parser";
import { getDefaultFetcherOptions } from "../clients";
import type { FetcherOptions } from "./fetchers";

Expand All @@ -9,6 +8,25 @@ export interface Rule {
summary: string;
}

async function extractPdfText(buffer: ArrayBuffer): Promise<string> {
const { getDocument } = await import("pdfjs-dist/legacy/build/pdf.mjs");
const doc = await getDocument({ data: new Uint8Array(buffer) }).promise;
const pages: string[] = [];
for (let i = 1; i <= doc.numPages; i++) {
const page = await doc.getPage(i);
const content = await page.getTextContent();
let pageText = "";
for (const item of content.items) {
if ("str" in item) {
pageText += item.str;
if (item.hasEOL) pageText += "\n";
}
}
pages.push(pageText);
}
return pages.join("\n");
}

export const extractRules = async (
url: string,
options?: FetcherOptions,
Expand All @@ -19,8 +37,7 @@ export const extractRules = async (
if (buffer === null) {
return null;
}
const content = await parsepdf(buffer);
const text = content.pages.join("\n");
const text = await extractPdfText(buffer);
const matches = Array.from(text.matchAll(RULE_TABLE_PATTERN));
const rules: Rule[] = [];
for (const match of matches) {
Expand Down
Loading