holm/se-scraper
1
0
Fork 0
forked from extern/se-scraper
Code Issues Pull Requests Packages Projects Releases Wiki Activity

minor stuff

Browse Source
This commit is contained in:
Nikolai Tschacher 2019-06-11 18:33:11 +02:00
parent 7e06944fa1
commit 35943e7449
4 changed files with 57 additions and 28 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@ -159,7 +159,7 @@ This will scrape with **three** browser instance each having their own IP addres
## Examples
* [Reuse existing browser](examples/quickstart.js) yields [these results](examples/results/data.json)
* [Reuse existing browser](examples/multiple_search_engines.js) yields [these results](examples/results/multiple_search_engines.json)
* [Simple example scraping google](examples/quickstart.js) yields [these results](examples/results/data.json)
* [Simple example scraping baidu](examples/baidu.js) yields [these results](examples/results/baidu.json)
* [Scrape with one proxy per browser](examples/proxies.js) yields [these results](examples/results/proxyresults.json)

2
examples/multiple_search_engines.js
View File

@ -7,7 +7,7 @@ const se_scraper = require('./../src/node_scraper.js');
sleep_range: '[1,1]',
debug_level: 1,
headless: true,
output_file: `multiple_search_engines.json`
output_file: `examples/results/multiple_search_engines.json`
};
let scrape_job = {

80
multiple_search_engines.json → examples/results/multiple_search_engines.json
View File

@ -1,7 +1,7 @@
{
"news": {
"1": {
"time": "Tue, 11 Jun 2019 16:25:41 GMT",
"time": "Tue, 11 Jun 2019 16:32:56 GMT",
"no_results": false,
"effective_query": "",
"num_results": "195.000.000 Ergebnisse",
@ -61,16 +61,30 @@
"snippet": "News zu Stars und VIPs: Ob Hollywood-Schauspieler, TV-Liebling, C-Promi oder Supermodel - auf GALA.de verpassen Sie keine News zu ihrem Star.",
"visible_link": "https://www.gala.de/stars/news",
"rank": 8
},
{
"link": "https://www.bbc.com/news",
"title": "Home - BBC News",
"snippet": "Visit BBC News for up-to-the-minute news, breaking news, video, audio and feature stories. BBC News provides trusted World and UK news as well as local and regional perspectives. Also ...",
"visible_link": "https://www.bbc.com/news",
"rank": 9
},
{
"link": "https://www.cnn.com/",
"title": "CNN - Breaking News, Latest News and Videos",
"snippet": "View the latest news and breaking news today for U.S., world, weather, entertainment, politics and health at CNN.com.",
"visible_link": "https://www.cnn.com",
"rank": 10
}
]
}
},
"se-scraper": {
"1": {
"time": "Tue, 11 Jun 2019 16:25:43 GMT",
"time": "Tue, 11 Jun 2019 16:32:58 GMT",
"no_results": false,
"effective_query": "",
"num_results": "48.300 Ergebnisse",
"num_results": "48.200 Ergebnisse",
"results": [
{
"link": "http://konjugator.reverso.net/konjugation-franzosisch-verb-ne%20pas%20se%20scraper.html",
@ -80,24 +94,24 @@
"rank": 1
},
{
"link": "https://www.amazon.de/ADAALEN-Silikon-Frischk%C3%83%C2%A4se-Scraper-Anr%C3%83%C2%BChrspatel/dp/B01KVXVB6C",
"title": "ADAALEN Silikon Frischkäse Butter Scraper Butter Batter ...",
"snippet": "Amazon.de: Küchen- und Haushaltsartikel online - ADAALEN Silikon Frischkäse Butter Scraper Butter Batter Anrührspatel. Beschreibung: Die Silikon Sahnebutter Schaber aus reinem Silikon. Mit einem.",
"visible_link": "https://www.amazon.de/ADAALEN-Silikon-Frischkäse-Scraper-Anrührspatel/dp/B01KVXVB6C",
"link": "https://github.com/NikolaiT/se-scraper",
"title": "GitHub - NikolaiT/se-scraper: Javascript scraping …",
"snippet": "Search Engine Scraper - se-scraper. This node module allows you to scrape search engines concurrently with different proxies. If you don't have much technical experience or don't want to purchase proxies, you can use my scraping service.",
"visible_link": "https://github.com/NikolaiT/se-scraper",
"rank": 2
},
{
"link": "https://www.amazon.de/Moppi-Silikon-Frischk%C3%83%C2%A4se-Scraper-Anr%C3%83%C2%BChrspatel/dp/B01K8JT38C",
"title": "Moppi Silikon Frischkäse Butter Scraper Butter Batter ...",
"snippet": "Amazon.de: Küchen- und Haushaltsartikel online - Moppi Silikon Frischkäse Butter Scraper Butter Batter Anrührspatel. Beschreibung: Die Silikon Sahnebutter Schaber aus reinem Silikon. Mit einem.",
"visible_link": "https://www.amazon.de/Moppi-Silikon-Frischkäse-Scraper-Anrührspatel/dp/B01K8JT38C",
"link": "https://www.amazon.de/Calli-Silikon-Frischk%C3%83%C2%A4se-Scraper-Anr%C3%83%C2%BChrspatel/dp/B01JJ96FPG",
"title": "Calli Silikon Frischkäse Butter Scraper Butter Batter ...",
"snippet": "Amazon.de: Küchen- und Haushaltsartikel online - Calli Silikon Frischkäse Butter Scraper Butter Batter Anrührspatel. Beschreibung: Die Silikon Sahnebutter Schaber aus reinem Silikon. Mit einem.",
"visible_link": "https://www.amazon.de/Calli-Silikon-Frischkäse-Scraper-Anrührspatel/dp/B01JJ96FPG",
"rank": 3
},
{
"link": "http://conjugador.reverso.net/conjugacion-frances-verbo-se%20scraper.html",
"title": "Conjugación se scraper | Conjugar verbo se …",
"snippet": "Conjugación verbo: conjugar se scraper en francés, ver modelos de conjugación francés, verbos irregulares, reglas de conjugación del verbo francés",
"visible_link": "conjugador.reverso.net/conjugacion-frances-verbo-se scraper.html",
"link": "https://snyk.io/test/github/NikolaiT/se-scraper",
"title": "Vulnerability report for NikolaiT/se-scraper | Snyk",
"snippet": "No vulnerabilities found in se-scraper. View the full report.",
"visible_link": "https://snyk.io/test/github/NikolaiT/se-scraper",
"rank": 4
},
{
@ -108,25 +122,39 @@
"rank": 5
},
{
"link": "https://github.com/NikolaiT/se-scraper",
"title": "GitHub - NikolaiT/se-scraper: Javascript scraping …",
"snippet": "07.02.2019 · Search Engine Scraper - se-scraper. This node module allows you to scrape search engines concurrently with different proxies. If you don't have much technical experience or don't want to purchase proxies, you can use my scraping service.",
"visible_link": "https://github.com/NikolaiT/se-scraper",
"link": "https://www.idealo.de/preisvergleich/OffersOfProduct/3071147_-multi-purpose-scraper-toko.html",
"title": "Toko Multi-Purpose Scraper ab 3,99 € | Preisvergleich bei ...",
"snippet": "Ver­sand in­ner­halb von 3 Werk­ta­gen nach Zah­lungs­ein­gang.",
"visible_link": "https://www.idealo.de/preisvergleich/OffersOfProduct/3071147_-multi-purpose-scraper...",
"rank": 6
},
{
"link": "https://www.idealo.at/preisvergleich/OffersOfProduct/3071147_-multi-purpose-scraper-toko.html",
"title": "Toko Multi-Purpose Scraper ab € 4,48 | Preisvergleich bei ...",
"snippet": "Bereits ab € 4,48 Große Shopvielfalt Testberichte & Meinungen | Jetzt Toko Multi-Purpose Scraper Ski-Zubehör günstig kaufen bei idealo.at",
"visible_link": "https://www.idealo.at/preisvergleich/OffersOfProduct/3071147_-multi-purpose-scraper...",
"rank": 7
},
{
"link": "https://woerterbuch.reverso.net/franzosisch-definitionen/se+scraper",
"title": "se scraper Definition | Französisch Definition Wörterbuch ...",
"snippet": "Definition se scraper Franzosisch, Synonym und Antonym, Siehe auch 'scrapeur',scrap',scrapie',scalper'",
"visible_link": "https://woerterbuch.reverso.net/franzosisch-definitionen/se+scraper",
"rank": 7
},
{
"link": "https://www.sonic-equipment.com/se/scraper-10233.html",
"title": "Scraper - sonic-equipment.com",
"snippet": "Universal scraper for removing sealants, filler, gaskets etc.",
"visible_link": "https://www.sonic-equipment.com/se/scraper-10233.html",
"rank": 8
},
{
"link": "https://github.com/NikolaiT/se-scraper/blob/master/examples/results/data.json",
"title": "se-scraper/data.json at master · NikolaiT/se-scraper · GitHub",
"snippet": "Javascript scraping module based on puppeteer for many different search engines... - NikolaiT/se-scraper",
"visible_link": "https://github.com/NikolaiT/se-scraper/blob/master/examples/results/data.json",
"rank": 9
},
{
"link": "https://www.friatec.de/content/friatec/en/Technical-Plastics/FRIATOOLS-Technical-Equipment/Downloads/index.html",
"title": "Downloads",
"snippet": "Downloads Online Catalog. Product Range 2018. General Brochures. Technical Plastics - Image brochure. Product Range 2019 (PDF) KATALOG 2018 (SK) FRIATEC Image brochure. Safety data sheet care spray. Brochures Fusion Units . FRIAMAT prime and basic. FRIAMAT prime eco (2018) FRIAMAT basic eco (2018) FRIAMAT print eco (2018) The new FRIAMAT. Flyer FRIAMAT prime, basic eco. …",
"visible_link": "https://www.friatec.de/.../FRIATOOLS-Technical-Equipment/Downloads/index.html",
"rank": 10
}
]
}

1
src/node_scraper.js
View File

@ -377,6 +377,7 @@ class ScrapeManager {
}
if (this.config.output_file) {
log(this.config, 1, `Writing results to ${this.config.output_file}`);
write_results(this.config.output_file, JSON.stringify(results, null, 4));
}