Nick: refactor

2024-07-03 18:01:17 -03:00
parent 90cf799a3c
commit 90c54c32fd
7 changed files with 391 additions and 359 deletions
@@ -0,0 +1,98 @@
+import axios from "axios";
+import { logScrape } from "../../../services/logging/scrape_log";
+import { generateRequestParams } from "../single_url";
+import { fetchAndProcessPdf } from "../utils/pdfProcessor";
+import { universalTimeout } from "../global";
+
+export async function scrapWithPlaywright(
+  url: string,
+  waitFor: number = 0,
+  headers?: Record<string, string>,
+  pageOptions: { parsePDF?: boolean } = { parsePDF: true }
+): Promise<{ content: string; pageStatusCode?: number; pageError?: string }> {
+  const logParams = {
+    url,
+    scraper: "playwright",
+    success: false,
+    response_code: null,
+    time_taken_seconds: null,
+    error_message: null,
+    html: "",
+    startTime: Date.now(),
+  };
+
+  try {
+    const reqParams = await generateRequestParams(url);
+    // If the user has passed a wait parameter in the request, use that
+    const waitParam = reqParams["params"]?.wait ?? waitFor;
+
+    const response = await axios.post(
+      process.env.PLAYWRIGHT_MICROSERVICE_URL,
+      {
+        url: url,
+        wait_after_load: waitParam,
+        headers: headers,
+      },
+      {
+        headers: {
+          "Content-Type": "application/json",
+        },
+        timeout: universalTimeout + waitParam, // Add waitParam to timeout to account for the wait time
+        transformResponse: [(data) => data], // Prevent axios from parsing JSON automatically
+      }
+    );
+
+    if (response.status !== 200) {
+      console.error(
+        `[Playwright] Error fetching url: ${url} with status: ${response.status}`
+      );
+      logParams.error_message = response.data?.pageError;
+      logParams.response_code = response.data?.pageStatusCode;
+      return {
+        content: "",
+        pageStatusCode: response.data?.pageStatusCode,
+        pageError: response.data?.pageError,
+      };
+    }
+
+    const contentType = response.headers["content-type"];
+    if (contentType && contentType.includes("application/pdf")) {
+      logParams.success = true;
+      return await fetchAndProcessPdf(url, pageOptions?.parsePDF);
+    } else {
+      const textData = response.data;
+      try {
+        const data = JSON.parse(textData);
+        const html = data.content;
+        logParams.success = true;
+        logParams.html = html;
+        logParams.response_code = data.pageStatusCode;
+        logParams.error_message = data.pageError;
+        return {
+          content: html ?? "",
+          pageStatusCode: data.pageStatusCode,
+          pageError: data.pageError,
+        };
+      } catch (jsonError) {
+        logParams.error_message = jsonError.message || jsonError;
+        console.error(
+          `[Playwright] Error parsing JSON response for url: ${url} -> ${jsonError}`
+        );
+        return { content: "" };
+      }
+    }
+  } catch (error) {
+    if (error.code === "ECONNABORTED") {
+      logParams.error_message = "Request timed out";
+      console.log(`[Playwright] Request timed out for ${url}`);
+    } else {
+      logParams.error_message = error.message || error;
+      console.error(`[Playwright] Error fetching url: ${url} -> ${error}`);
+    }
+    return { content: "" };
+  } finally {
+    const endTime = Date.now();
+    logParams.time_taken_seconds = (endTime - logParams.startTime) / 1000;
+    await logScrape(logParams);
+  }
+}