scrapper-aacr.mjs

import fs from "fs";
import path from "path";

const SESSION_LIST_URL =
  "https://www.abstractsonline.com/oe3/Program/20273/Search/10/Results?page=1&pagesize=50&total_pages=3&total_entries=122&sort=1&order=asc";

const HEADERS_1 = {
  Accept: "application/json",
  "Content-Type": "application/json",
  "User-Agent":
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/135.0.0.0 Safari/537.36",
  "X-Requested-With": "XMLHttpRequest",
  Backpack: "2be5f4ce-1db3-45f5-ac01-33d85c347bf8",
  Cookie:
    "backpack=2be5f4ce-1db3-45f5-ac01-33d85c347bf8; backpackExpiration=Mon%2C%2021%20Apr%202025%2020%3A46%3A53; AWSALB=TeM+pJyO7in2ZX4aLJz/cM5psdjo6UxBakTPTguUf3B08+DAZa+QyxHjwnb+Usf1eaigU4ZGw7Rlx2KNohT4F4xHND9AxIhBwMoBfLD9fCLI87dI7YvOGFzWsOLU; AWSALBCORS=TeM+pJyO7in2ZX4aLJz/cM5psdjo6UxBakTPTguUf3B08+DAZa+QyxHjwnb+Usf1eaigU4ZGw7Rlx2KNohT4F4xHND9AxIhBwMoBfLD9fCLI87dI7YvOGFzWsOLU",
};
async function fetchJSON1(url) {
  const res = await fetch(url, { headers: HEADERS_1 });
  if (!res.ok) throw new Error(`HTTP ${res.status}: ${res.statusText}`);
  return res.json();
}
const HEADERS = {
  Accept: "application/json",
  "Content-Type": "application/json",
  "User-Agent":
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/135.0.0.0 Safari/537.36",
  "X-Requested-With": "XMLHttpRequest",
  Backpack: "2be5f4ce-1db3-45f5-ac01-33d85c347bf8",
  Cookie:
    "backpack=2be5f4ce-1db3-45f5-ac01-33d85c347bf8; backpackExpiration=Mon%2C%2021%20Apr%202025%2020%3A46%3A53",
};
async function fetchJSON(url) {
  const res = await fetch(url, { headers: HEADERS });
  if (!res.ok) throw new Error(`HTTP ${res.status}: ${res.statusText}`);
  return res.json();
}

function extractAffiliationFromAuthorBlock(authorBlock) {
  if (!authorBlock) return null;
  const plainText = authorBlock.replace(/<[^>]+>/g, "").trim();
  const parts = plainText.split(". ");
  return parts.length > 1 ? parts[1].trim() : null;
}

function toCSV(data) {
  const header = [
    "Session Title",
    "Session Date",
    "Start Time",
    "Presenter",
    "Presentation Title",
    "Affiliation",
  ];
  const rows = data.map((row) => [
    row.sessionTitle,
    row.sessionDate,
    row.startTime,
    row.presenter,
    row.title,
    row.affiliation,
  ]);
  return [header, ...rows]
    .map((r) =>
      r.map((cell) => `"${String(cell).replace(/"/g, '""')}"`).join(",")
    )
    .join("\n");
}

async function scrape() {
  const sessionsResp = await fetchJSON1(SESSION_LIST_URL);
  const sessions = sessionsResp.Results.map((session) => ({
    id: session.Id,
    title: session.Body.trim(),
    datetime: session.Head,
    location: session.Foot,
  }));

  const allPresentations = [];

  for (const session of sessions) {
    try {
      const metadataUrl = `https://www.abstractsonline.com/oe3/Program/20273/Session/${session.id}`;
      const presentationsUrl = `${metadataUrl}/presentations`;

      const [metadata, presentations] = await Promise.all([
        fetchJSON(metadataUrl),
        fetchJSON(presentationsUrl),
      ]);

      for (const p of presentations) {
        if (!p.PresenterDisplayName) continue;

        allPresentations.push({
          sessionTitle: metadata.Title,
          sessionDate: metadata.Date,
          startTime: p.Start,
          presenter: p.PresenterDisplayName,
          title: p.Title,
          affiliation: extractAffiliationFromAuthorBlock(p.AuthorBlock),
        });
      }
    } catch (err) {
      console.error(`Failed to process session ${session.id}: ${err.message}`);
    }
  }

  // console.log(JSON.stringify(allPresentations, null, 2));
  // Convert to CSV and save to file
  const csv = toCSV(allPresentations);
  const __dirname = import.meta.dirname;
  const outputPath = path.join(__dirname, "./aacr_presenters.csv");
  fs.writeFileSync(outputPath, csv);
  console.log(`✅ CSV written to ${outputPath}`);
}

scrape().catch(console.error);