mirror of
https://github.com/orangecoding/fredy.git
synced 2026-06-16 12:31:07 +00:00
Scrapingant proxies (#59)
* preparing scraping ant proxies * adding general settings for scraping ant proxy * retrying with new ui settings
This commit is contained in:
committed by
GitHub
parent
a4501007ff
commit
2062aa11a3
@@ -1,16 +1,21 @@
|
||||
const axios = require('axios');
|
||||
const config = require('../../conf/config.json');
|
||||
|
||||
const { makeUrlResidential } = require('./scrapingAnt');
|
||||
//if ScrapingAnt got blocked, this http status is returned
|
||||
const BLOCKED_HTTP_STATUS = 423;
|
||||
const MAX_RETRIES_SCRAPING_ANT = 3;
|
||||
const NOT_FOUND_HTTP_STATUS = 404;
|
||||
const MAX_RETRIES_SCRAPING_ANT = 10;
|
||||
const EXPECTED_STATUS_CODES = [BLOCKED_HTTP_STATUS, NOT_FOUND_HTTP_STATUS];
|
||||
|
||||
function makeDriver(headers = {}) {
|
||||
let cookies = '';
|
||||
|
||||
async function scrapingAntDriver(context, callback, tryResidentialProxy, retryCounter = 0) {
|
||||
async function scrapingAntDriver(context, callback, retryCounter = 0) {
|
||||
const proxyType = config.scrapingAnt?.proxy || 'datacenter';
|
||||
|
||||
try {
|
||||
const url = context.url;
|
||||
const url = proxyType === 'residential' ? makeUrlResidential(context.url) : context.url;
|
||||
const result = await axios({
|
||||
url,
|
||||
headers: {
|
||||
@@ -26,27 +31,16 @@ function makeDriver(headers = {}) {
|
||||
callback(null, result.data.content);
|
||||
} catch (exception) {
|
||||
/* eslint-disable no-console */
|
||||
if (exception.response?.status !== BLOCKED_HTTP_STATUS) {
|
||||
if (!EXPECTED_STATUS_CODES.includes(exception.response?.status)) {
|
||||
console.error(`Error while trying to scrape data from scraping ant. Received error: ${exception.message}`);
|
||||
callback(null, []);
|
||||
return;
|
||||
}
|
||||
|
||||
if (!tryResidentialProxy) {
|
||||
console.debug('ScrapingAnt got blocked out. Retrying with residential Proxy...');
|
||||
await scrapingAntDriver({ ...context, url: makeUrlResidential(context.url) }, callback, true, 0);
|
||||
} else if (retryCounter <= MAX_RETRIES_SCRAPING_ANT) {
|
||||
if (retryCounter <= MAX_RETRIES_SCRAPING_ANT) {
|
||||
retryCounter++;
|
||||
console.debug(`ScrapingAnt still got blocked retry ${retryCounter} / ${MAX_RETRIES_SCRAPING_ANT}`);
|
||||
await scrapingAntDriver(
|
||||
{
|
||||
...context,
|
||||
url: makeUrlResidential(context.url),
|
||||
},
|
||||
callback,
|
||||
true,
|
||||
retryCounter
|
||||
);
|
||||
console.debug(`ScrapingAnt got blocked. Retrying ${retryCounter} / ${MAX_RETRIES_SCRAPING_ANT}`);
|
||||
await scrapingAntDriver(context, callback, retryCounter);
|
||||
} else {
|
||||
console.error(`Error while trying to scrape data from scraping ant. Received error: ${exception.message}`);
|
||||
callback(null, []);
|
||||
|
||||
@@ -9,7 +9,7 @@ const isImmoscout = (id) => {
|
||||
exports.transformUrlForScrapingAnt = (url, id) => {
|
||||
if (isImmoscout(id)) {
|
||||
//only do calls to scrapingAnt when dealing with Immoscout
|
||||
url = `https://api.scrapingant.com/v1/general?url=${encodeURIComponent(url)}&proxy_type=residential`;
|
||||
url = `https://api.scrapingant.com/v1/general?url=${encodeURIComponent(url)}&proxy_type=datacenter`;
|
||||
}
|
||||
return url;
|
||||
};
|
||||
|
||||
Reference in New Issue
Block a user