Last active
August 31, 2018 12:53
-
-
Save KristerV/873bf14e9dc73aeed0d7db11b257fb79 to your computer and use it in GitHub Desktop.
Scrape Facebook Group
This file contains 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
/* | |
This will expand all of the posts and comments that is in the view. It will take a lot of time! | |
To use just paste this in your console (F12). | |
*/ | |
var previousScrollheight = 0 | |
scrollDown = function() { | |
var currentScrollheight = document.body.scrollHeight | |
var canScroll = currentScrollheight - previousScrollheight | |
previousScrollheight = document.body.scrollHeight | |
if (canScroll !== 0) { | |
window.scrollTo(0,currentScrollheight); | |
} | |
return canScroll | |
} | |
expandComments = function() { | |
var foundLinks = 0 | |
document.querySelectorAll(':not(.text_exposed) > .text_exposed_hide > .text_exposed_link > .see_more_link').forEach(function(item) { | |
item.click() | |
foundLinks++ | |
}) | |
document.querySelectorAll('[href="#"]').forEach(function(item){ | |
var whitelist = ["See more", "More option", "more comment", "replie"] | |
var blacklist = ["Hide", " hidden", "u_0_19"] | |
var blacklistRegexp = new RegExp(blacklist.join("|"), "i") | |
var whitelistResult = new RegExp(whitelist.join("|"), "i").test(item.innerHTML) | |
var blacklistResultHTML = !(blacklistRegexp.test(item.innerHTML)) | |
var blacklistResultClass = !(blacklistRegexp.test(item.className)) | |
var blacklistResultId = !(blacklistRegexp.test(item.id)) | |
if (whitelistResult && blacklistResultHTML && blacklistResultClass && blacklistResultId) { | |
foundLinks++ | |
item.click() | |
} | |
}) | |
return foundLinks | |
} | |
procedure = function() { | |
setTimeout(function(){ | |
var scrolled = scrollDown() | |
var expanded = expandComments() | |
console.log("Scrolled:", scrolled, ". Expanded:", expanded) | |
if (scrolled !== 0 && expanded !== 0) { | |
procedure() | |
} else { | |
console.log("Finished procedure") | |
setTimeout(function(){ | |
startOver() | |
}, 1000 * 60 * 1) | |
} | |
}, 10000) | |
} | |
var tries = 0 | |
startOver = function() { | |
if (tries < 10) { | |
console.log("Try:", tries) | |
tries++ | |
procedure() | |
} else { | |
console.log("Finished whole program.") | |
} | |
} | |
startOver() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment