mtrunkat

#!/bin/bash

# See https://github.com/docker-library/mongo/pull/63

docker run --rm --volumes-from my-mongo-server mongo unlink "/data/db/mongod.lock"
docker run --rm --volumes-from my-mongo-server mongo --repair

mtrunkat

# Here you choose the base Docker image for the actor. Apify provides the following images:
#  apify/actor-node-basic
#  apify/actor-node-chrome
#  apify/actor-node-puppeteer
# However, you can use any other image from Docker Hub.
# For more information, see https://apify.com/docs/actor#base-images
FROM apify/actor-node-basic

# Copy all files and directories from the directory to the Docker image
COPY . ./

mtrunkat

<section class="page-content">
  <h4>2016-11-24</h4>
  <ul> 
    <li>Web: Added a new feature ... </li> 
  </ul>
  
  <h4>2016-11-09</h4>
  <ul>
    <li>General: Increased the length limit ...</li>
    <li>Web: Showing more relevant statistics ...</li>

mtrunkat

<?xml version="1.0" encoding="utf-8"?>
<rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0">
  <channel>
    <title>Apifier_Release_Notes</title>
    <link>...</link>
    <description>...</description>
    <generator>Apifier - Crawler #1</generator>
    <lastBuildDate>Sun, 06 Sep 2009 16:20:00 UTC</lastBuildDate>

    <item>

mtrunkat

function pageFunction(context) {
  var $ = context.jQuery;
  // All h4 headings containing date - <h4>2016-11-24</h4>
  var headings = $('.page-content h4');
  // All descriptions - <ul><li>General: ...</li>...</ul>
  var lists = $('.page-content ul');

  // Iterate thru all release notes
  var result = [];
  for (var i = 0; i < headings.length; i ++) {

mtrunkat

[{
  "https://github.com/apas/athena": 100,
  "https://github.com/achillesrasquinha/bulbea": 99,
  "https://keratin.tech": 98,
  "https://github.com/dhruvio/js_express-parser-combinators": 97,
  "https://www.pagedash.com/": 96,
  "https://github.com/monostream/tifig": 95,
  "https://javalin.io/news/javalin-1.0.0-stable.html": 94,
  "http://www.goodoldweb.com/": 93,
  "http://vuemc.io": 92,

mtrunkat

function pageFunction(context) {
  var $ = context.jQuery
  var posts = $('.athing').toArray(); // All posts as array of DOM elements
  var $moreLink = $('.morelink');     // Link to next page
  
  // If crawler is scraping 2nd, 3rd, ... page then 
  // context.request.referrer.pageFunctionResult contains 
  // result from previous pages.
  var prevResult = context.request.referrer 
    ? context.request.referrer.pageFunctionResult 

mtrunkat

# Get private key

openssl pkcs12 -in yourP12File.pfx -nocerts -out privateKey.pem

# Get public key

openssl pkcs12 -in yourP12File.pfx -clcerts -nokeys -out publicCert.pem

mtrunkat

const express = require('express');

const { APIFY_CONTAINER_PORT, APIFY_CONTAINER_URL } = process.env;
const app = express()

app.get('/', (req, res) => {
  res.send('Hello World!');
});

app.listen(APIFY_CONTAINER_PORT, () => {

mtrunkat

const Apify = require('apify');

Apify.main(async () => {
    // Get queue and enqueue first url.
    const requestQueue = await Apify.openRequestQueue();
    const enqueue = async url => requestQueue.addRequest(new Apify.Request({ url }));
    await enqueue('https://news.ycombinator.com/');

    // Create crawler.
    const crawler = new Apify.PuppeteerCrawler({