Yellow-Pages-Scraper-withEmail

root = true

[*]
indent_style = space
indent_size = 4
charset = utf-8
trim_trailing_whitespace = true
insert_final_newline = true
end_of_line = lf

{
    "extends": "@apify"
}

# This file tells Git which files shouldn't be added to source control

.idea
node_modules

# First, specify the base Docker image. You can read more about
# the available images at https://sdk.apify.com/docs/guides/docker-images
# You can also use any other image from Docker Hub.
FROM apify/actor-node:16

# Second, copy just package.json and package-lock.json since it should be
# the only file that affects "npm install" in the next step, to speed up the build
COPY package*.json ./

# Install NPM packages, skip optional and development dependencies to
# keep the image small. Avoid logging too much and print the dependency
# tree for debugging
RUN npm --quiet set progress=false \
 && npm install --only=prod --no-optional \
 && echo "Installed NPM packages:" \
 && (npm list --only=prod --no-optional --all || true) \
 && echo "Node.js version:" \
 && node --version \
 && echo "NPM version:" \
 && npm --version

# Next, copy the remaining files and directories with the source code.
# Since we do this after NPM install, quick build will be really fast
# for most source file changes.
COPY . ./

# Optionally, specify how to launch the source code of your actor.
# By default, Apify's base Docker images define the CMD instruction
# that runs the Node.js source code using the command specified
# in the "scripts.start" section of the package.json file.
# In short, the instruction looks something like this:
#
# CMD npm start

{
    "title": "Yellowpages scraper input schema",
    "type": "object",
    "schemaVersion": 1,
    "properties": {
        "search": {
            "title": "Search",
            "type": "string",
            "editor": "textfield",
            "prefill": "Dentist",
            "description": "Query to search on Yellow Pages"
        },
        "location": {
            "title": "Location",
            "type": "string",
            "editor": "textfield",
            "prefill": "Los Angeles",
            "description": "Location to search entries in"
        },
        "startUrls": {
            "title": "Start URLs",
            "type": "array",
            "editor": "requestListSources",
            "description": "List of URLs that will be crawled."
        },
        "maxItems": {
            "title": "Max items",
            "type": "integer",
            "minimum": 0,
            "prefill": 200,
            "description": "Maximum number of outputted results"
        },
        "extendOutputFunction": {
            "title": "Extend output function",
            "type": "string",
            "editor": "javascript",
            "description": "A function which result will get merged with the default result",
            "prefill": "($, record) => {\n    return {};\n}",
            "sectionCaption": "Advanced options"
        },
        "proxyConfiguration": {
            "title": "Proxy configuration",
            "type": "object",
            "editor": "proxy",
            "description": "In this case the best option is usually no proxy. Otherwise US or UK proxies work best.",
            "prefill": { "useApifyProxy": false }
        }
    }
}

{
    "env": { "npm_config_loglevel": "silent" }
}

1// This is the main Node.js source code file of your actor.
2
3// Import Apify SDK. For more information, see https://sdk.apify.com/
4const Apify = require('apify');
5
6Apify.main(async () => {
7    const input= await Apify.getInput();
8    const run=await Apify.call('petr_cermak/yellow-pages-scraper', input);
9    const axios=require('axios');
10    const cheerio=require('cheerio');
11    var dataset=await Apify.openDataset(run.defaultDatasetId);
12    var ar=await dataset.getData();
13    var data=ar.items;
14    for(var i=0;i<data.length;i++){
15    var obj=data[i];
16    var res=await axios.get(obj.url);
17    var $=cheerio.load(res.data);
18    var emails=$(".email-business").attr("href");
19    obj.email="";
20    if(emails==undefined){
21        obj.email="none found";
22    }else{
23        var array=emails.split(":");
24        obj.email=array[1];
25    }
26    await Apify.pushData(obj);
27    }
28});

{
    "name": "project-empty",
    "version": "0.0.1",
    "description": "This is a boilerplate of an Apify actor.",
    "dependencies": {
        "apify": "^2.3.2"
    },
    "devDependencies": {
        "@apify/eslint-config": "^0.1.3",
        "eslint": "^7.0.0"
    },
    "scripts": {
        "start": "node main.js",
        "lint": "./node_modules/.bin/eslint ./src --ext .js,.jsx",
        "lint:fix": "./node_modules/.bin/eslint ./src --ext .js,.jsx --fix",
        "test": "echo \"Error: oops, the actor has no tests yet, sad!\" && exit 1"
    },
    "author": "It's not you it's me",
    "license": "ISC"
}