// ==UserScript==
// @name Eza's Tumblr Scrape
// @namespace https://inkbunny.net/ezalias
// @description Creates a new page showing just the images from any Tumblr
// @license MIT
// @license Public domain / No rights reserved
// @include http://*?ezastumblrscrape*
// @include https://*?ezastumblrscrape*
// @include http://*/ezastumblrscrape*
// @include http://*.tumblr.com/
// @include https://*.tumblr.com/
// @include http://*.tumblr.com/page/*
// @include https://*.tumblr.com/page/*
// @include http://*.tumblr.com/tagged/*
// @include https://*.tumblr.com/tagged/*
// @include http://*.tumblr.com/post/*
// @include https://*.tumblr.com/post/*
// @include http://*.tumblr.com/archive
// @include http://*.co.vu/*
// @exclude */photoset_iframe/*
// @exclude *imageshack.us*
// @exclude *imageshack.com*
// @exclude *//scmplayer.*
// @exclude *//wikplayer.*
// @grant GM_registerMenuCommand
// @version 5.7
// @downloadURL none
// ==/UserScript==
// Create an imaginary page on the relevant Tumblr domain, mostly to avoid the ridiculous same-origin policy for public HTML pages. Populate page with all images from that Tumblr. Add links to this page on normal pages within the blog.
// This script also works on off-site Tumblrs, by the way - just add /archive?ezastumblrscrape?scrapewholesite after the ".com" or whatever. Sorry it's not more concise.
// Make it work, make it fast, make it pretty - in that order.
// TODO:
// I'll have to add filtering as some kind of text input... and could potentially do multi-tag filtering, if I can reliably identify posts and/or reliably match tag definitions to images and image sets.
// This is a good feature for doing /scrapewholesite to get text links and then paging through them with fancy dynamic presentation nonsense. Also: duplicate elision.
// I'd love to do some multi-scrape stuff, e.g. scraping both /tagged/homestuck and /tagged/art, but that requires communication between divs to avoid constant repetition.
// post-level detection would also be great because it'd let me filter out reblogs. fuck all these people with 1000-page tumblrs, shitty animated gifs in their theme, infinite scrolling, and NO FUCKING TAGS. looking at you, http://neuroticnick.tumblr.com/post/16618331343/oh-gamzee#dnr - you prick.
// Look into Tumblr Saviour to see how they handle and filter out text posts.
// Add a convenient interface for changing options? "Change browsing options" to unhide a div that lists every ?key=value pair, with text-entry boxes or radio buttons as appropriate, and a button that pushes a new URL into the address bar and re-hides the div. Would need to be separate from thumbnail toggle so long as anything false is suppressed in get_url or whatever.
// Dropdown menus? Thumbnails yes/no, Pages At Once 1-20. These change the options_map settings immediately, so next/prev links will use them. Link to Apply Changes uses same ?startpage as current.
// Could I generalize that the way I've generalized Image Glutton? E.g., grab all links from a Pixiv gallery page, show all images and all manga pages.
// Possibly @include any ?scrapeeverythingdammit to grab all links and embed all pictures found on them. single-jump recursive web mirroring. (fucking same-domain policy!)
// now that I've got key-value mapping, add a link for 'view original posts only (experimental).' er, 'hide reblogs?' difficult to accurately convey.
// make it an element of the post-scraping function. then it would also work on scrape-whole-tumblr.
// better yet: call it separately, then use the post-scraping function on each post-level chunk of HTML. i.e. call scrape_without_reblogs from scrape_whole_tumblr, split off each post into strings, and call soft_scrape_page( single_post_string ) to get all the same images.
// or would it be better to get all images from any post? doing this by-post means we aren't getting theme nonsense (mostly).
// maybe just exclude images where a link to another tumblr happens before the next image... no, text posts could screw that up.
// general post detection is about recognizing patterns. can we automate it heuristically? bear in mind it'd be done at least once per scrape-page, and possibly once per tumblr-page.
// user b84485 seems to be using the scrape-whole-site option to open image links in tabs, and so is annoyed by the 500/1280 duplicates. maybe a 'remove duplicates' button after the whole site's done?
// It's a legitimately good idea. Lord knows I prefer opening images in tabs under most circumstances.
// Basically I want a "Browse Links" page instead of just "grab everything that isn't nailed down."
// http://mekacrap.tumblr.com/post/82151443664/oh-my-looks-like-theres-some-pussy-under#dnr - lots of 'read more' stuff, for when that's implemented.
// eza's tumblr scrape: "read more" might be tumblr standard.
// e.g.
// http://c-enpai.tumblr.com/ - interesting content visible in /archive, but every page is 'themed' to be a blank front page. wtf.
// chokes on multi-thousand-page tumblrs like actual-vriska, at least when listing all pages. it's just link-heavy text. maybe skip having a div for every page and just append to one div. or skip divs and append to the raw document innerHTML. it could be a memory thing, if ajax elements are never destroyed.
// multi-thousand-page tumblrs make "find image links from all pages" choke. massive memory use, massive CPU load. ridiculous. it's just text. (alright, it's links and ajax requests, but it's doggedly linear.)
// maybe skip individual divs and append the raw pile-of-links hypertext into one div. or skip divs entirely and append it straight to the document innerHTML.
// could it be a memory leak thing? are ajax elements getting properly released and destroyed when their scope ends? kind of ridiculous either way, considering we're holding just a few kilobytes of text per page.
// try re-using the same ajax object.
/* Assorted notes from another text file
. eza's tumblr fixiv? de-style everything by simply erasing the ";
document.body.innerHTML += css_block; // Has to go in all at once or the browser "helpfully" closes the style tag upon evaluation
var mydiv = document.getElementById( "maindiv" ); // I apologize for the generic names. This script used to be a lot simpler.
// Identify options in URL (in the form of ?key=value pairs)
var key_value_array = window.location.href.split( '?' ); // Knowing how to do it the hard way is less impressive than knowing how not to do it the hard way.
key_value_array.shift(); // The first element will be the site URL. Durrrr.
for( dollarsign of key_value_array ) { // forEach( key_value_array ), including clumsy homage to $_
var this_pair = dollarsign.split( '=' ); // Split key=value into [key,value] (or sometimes just [key])
if( this_pair.length < 2 ) { this_pair.push( true ); } // If there's no value for this key, make its value boolean True
if( this_pair[1] == "false " ) { this_pair[1] = false; } // If the value is the string "false" then make it False - note fun with 1-ordinal "length" and 0-ordinal array[element].
else if( !isNaN( parseInt( this_pair[1] ) ) ) { this_pair[1] = parseInt( this_pair[1] ); } // If the value string looks like a number, make it a number
options_map[ this_pair[0] ] = this_pair[1]; // options_map.key = value
}
if( options_map.find[ options_map.find.length - 1 ] == "/" ) { options_map.find = options_map.find.substring( 0, options_map.find.length - 1 ); } // Prevents .com//page/2
// if( options_map.find.indexOf( '/chrono' ) > 0 ) { options_map.chrono = true; } else { options_map.chrono = false; } // False case, to avoid unexpected persistence? Hm.
// Convert old URL options to new key-value pairs
if( options_map[ "scrapewholesite" ] ) { options_map.scrapemode = "scrapewholesite"; options_map.scrapewholesite = false; }
if( options_map[ "everypost" ] ) { options_map.scrapemode = "everypost"; options_map.everypost = false; }
if( options_map[ "thumbnails" ] == true ) { options_map.thumbnails = "fixed-width"; } // Replace the original valueless key with the default value
document.body.className = options_map.thumbnails; // E.g. fixed-width, fixed-height, as matches the CSS. Persistent thumbnail options. Failsafe = original size.
// Oh yeah, we have to do this -after- options_map.find is defined:
site_and_tags = window.location.protocol + "//" + window.location.hostname + options_map.find; // e.g. http: + // + example.tumblr.com + /tagged/sherlock
// Grab an empty page so that duplicate-removal hides whatever junk is on every single page
// This is DEBUG-ish. It might be slow, barring caching. It might not work due to asynchrony. It could block actual content thanks to 'my best posts' sidebars.
// Wonky in scrapmode=everypost, because we have to block /post/ links that appear on every page (e.g. commissions).
// Could use /page/1 for that? It'd be faster.
// Might be best left to browse modes because of sidebar crap. Some "best" images might get skipped. Still: "Not all images are guaranteed to appear."
if( options_map.startpage != 1 ) { exclude_content_example( site_and_tags + '/page/100000' ); } // Not on first page, to fix e.g. jeffmacanolinsfw.tumblr.com
// Add tags to title, for archival and identification purposes
document.title += options_map.find.split('/').join(' '); // E.g. /tagged/example/chrono -> "tagged example chrono"
// In Chrome, /archive pages monkey-patch and overwrite Promise.all and Promise.resolve.
// Clunky solution to clunky problem: grab the default property from a fresh iframe.
// Big thanks to inu-no-policeman for the iframe-based solution. Prototypes were not helpful.
var iframe = document.createElement( 'iframe' );
document.body.appendChild( iframe );
window['Promise'] = iframe.contentWindow['Promise'];
document.body.removeChild( iframe );
mydiv.innerHTML = "Not all images are guaranteed to appear. "; // Thanks to JS's wacky accomodating nature, mydiv is global despite appearing in an if-else block.
// Go to image browser or link scraper according to URL options.
switch( options_map.scrapemode ) {
case "scrapewholesite": scrape_whole_tumblr(); break;
case "everypost": new_embedded_display(); break;
default: scrape_tumblr_pages();
}
} else { // If it's just a normal Tumblr page, add a link to the appropriate /ezastumblrscrape URL
// Add link(s) to the standard "+Follow / Dashboard" nonsense. Before +Follow, I think - to avoid messing with users' muscle memory.
// This is currently beyond my ability to dick with JS through a script in a plugin. Let's kludge it for immediate usability.
// kludge by Ivan - http://userscripts-mirror.org/scripts/review/65725.html
var url = window.location.protocol + "//" + window.location.hostname + "/archive?ezastumblrscrape?scrapewholesite?find=" + window.location.pathname;
// Preserve /tagged/tag/chrono, etc. Also preserve http: vs https: via "location.protocol".
if( url.indexOf( "/page/chrono" ) < 0 ) { // Basically checking for posts /tagged/page, thanks to Detective-Pony. Don't even ask.
if( url.lastIndexOf( "/page/" ) > 0 ) { url = url.substring( 0, url.lastIndexOf( "/page/" ) ); } // Don't include e.g. /page/2. We'll add that ourselves.
if( url.lastIndexOf( "/post/" ) > 0 ) { url = url.substring( 0, url.lastIndexOf( "/post" ) ); }
// On individual posts, the link should scrape the main page
}
// "Don't clean this up. It's not permanent."
// Fuck it, it works and it's fragile. Just boost its z-index so it stops getting covered.
var scrape_button = document.createElement("a");
scrape_button.setAttribute( "style", "position: absolute; top: 26px; right: 1px; padding: 2px 0 0; width: 50px; height: 18px; display: block; overflow: hidden; -moz-border-radius: 3px; background: #777; color: #fff; font-size: 8pt; text-decoration: none; font-weight: bold; text-align: center; line-height: 12pt; z-index: 1000; " );
scrape_button.setAttribute("href", url);
scrape_button.innerHTML = "Scrape";
var body_ref = document.getElementsByTagName("body")[0];
body_ref.appendChild(scrape_button);
// Pages where the button gets split (i.e. clicking top half only redirects tiny corner iframe) are probably loading this script separately in the iframe.
// Which means you'd need to redirect the window instead of just linking. Bluh.
// Greasemonkey supports user commands through its add-on menu! Thus: no more manually typing /archive?ezastumblrscrape?scrapewholesite on uncooperative blogs.
GM_registerMenuCommand( "Scrape whole Tumblr blog", go_to_scrapewholesite );
// If a page is missing (post deleted, blog deleted, name changed) a reblog can often be found based on the URL
// Ugh, these should only appear on /post/ pages.
// Naming these commands is hard. Both look for reblogs, but one is for if the post you're on is already a reblog.
// Maybe "because this Tumblr changed names / moved / is missing" versus "because this reblog got deleted?" Newbs might not know either way.
// "As though" this blog is missing / this post is missing?
// "Search for this Tumblr under a different name" versus "search for other blogs that've reblogged this?"
GM_registerMenuCommand( "Google for reblogs of this original Tumblr post", google_for_reblogs );
GM_registerMenuCommand( "Google for other instances of this Tumblr reblog", google_for_reblogs_other ); // two hard problems
}
function go_to_scrapewholesite() {
let redirect = window.location.protocol + "//" + window.location.hostname + "/archive?ezastumblrscrape?scrapewholesite?find=" + window.location.pathname;
window.location.href = redirect;
}
function google_for_reblogs() {
let blog_name = window.location.href.split('/')[2].split('.')[0]; // e.g. http//example.tumblr.com -> example
let content = window.location.href.split('/').pop(); // e.g. http//example.tumblr.com/post/12345/hey-i-drew-this -> hey-i-drew-this
let redirect = "https://google.com/search?q=tumblr " + blog_name + " " + content;
window.location.href = redirect;
}
function google_for_reblogs_other() {
let content = window.location.href.split('/').pop().split('-'); // e.g. http//example.tumblr.com/post/12345/hey-i-drew-this -> hey,i,drew,this
let blog_name = content.shift(); // e.g. examplename-hey-i-drew-this -> examplename
content = content.join('-');
let redirect = "https://google.com/search?q=tumblr " + blog_name + " " + content;
window.location.href = redirect;
}
// ------------------------------------ Whole-site scraper for use with DownThemAll ------------------------------------ //
// Monolithic scrape-whole-site function, recreating the original intent (before I added pages and made it a glorified multipage image browser)
function scrape_whole_tumblr() {
var highest_known_page = 0;
options_map.startpage = 1; // Reset to default, because other values do goofy things to the image-browsing links below
// Link to image-viewing version, preserving current tags
mydiv.innerHTML += "
";
// Find out how many pages we need to scrape.
if( isNaN( options_map.lastpage ) ) {
// Find upper bound in a small number of fetches. Ideally we'd skip this - some themes list e.g. "Page 1 of 24." I think that requires back-end cooperation.
mydiv.innerHTML += "Finding out how many pages are in " + site_and_tags.substring( site_and_tags.indexOf( '/' ) + 2 ) + ":
";
// Returns page number if there's no Next link, or negative page number if there is a Next link.
// Only for use on /mobile pages; relies on Tumblr's shitty standard theme
function test_next_page( body ) {
var link_index = body.indexOf( 'rel="canonical"' ); //
var page_index = body.indexOf( '/page/', link_index );
var terminator_index = body.indexOf( '"', page_index );
var this_page = parseInt( body.substring( page_index+6, terminator_index ) );
if( body.indexOf( '>next<' ) > 0 ) { return -this_page; } else { return this_page }
}
// Generates an array of length "steps" between given boundaries - or near enough, for sanity's sake
function array_between_bounds( lower_bound, upper_bound, steps ) {
if( lower_bound > upper_bound ) { // Swap if out-of-order.
var temp = lower_bound; lower_bound = upper_bound, upper_bound = temp;
}
var bound_range = upper_bound - lower_bound;
if( steps > bound_range ) { steps = bound_range; } // Steps <= bound_range, but steps > 1 to avoid division by zero:
var pages_per_test = parseInt( bound_range / steps ); // Steps-1 here, so first element is lower_bound & last is upper_bound. Off-by-one errors, whee...
var range = Array( steps )
.fill( lower_bound )
.map( (value,index) => value += index * pages_per_test );
range.push( upper_bound );
return range;
}
// Given a (presumably sorted) list of page numbers, find the last that exists and the first that doesn't exist.
function find_reasonable_bound( test_array ) {
return Promise.all( test_array.map( pagenum => fetch( site_and_tags + '/page/' + pagenum + '/mobile' ) ) )
.then( responses => Promise.all( responses.map( response => response.text() ) ) )
.then( pages => pages.map( page => test_next_page( page ) ) )
.then( numbers => {
var lower_index = -1;
numbers.forEach( (value,index) => { if( value < 0 ) { lower_index++; } } ); // Count the negative numbers (i.e., count the pages with known content)
if( lower_index < 0 ) { lower_index = 0; }
var bounds = [ Math.abs(numbers[lower_index]), numbers[lower_index+1] ]
mydiv.innerHTML += "Last page is between " + bounds[0] + " and " + bounds[1] + ". ";
return bounds;
} )
}
// Repeatedly narrow down how many pages we're talking about; find a reasonable "last" page
find_reasonable_bound( [2, 10, 100, 1000, 10000, 100000] ) // Are we talking a couple pages, or a shitload of pages?
.then( pair => find_reasonable_bound( array_between_bounds( pair[0], pair[1], 10 ) ) ) // Narrow it down. Fewer rounds of more fetches works best.
.then( pair => find_reasonable_bound( array_between_bounds( pair[0], pair[1], 10 ) ) ) // Time is round count, fetches add up, selectivity is fetches x fetches.
// Quit fine-tuning numbers and just conditional in some more testing for wide ranges.
.then( pair => { if( pair[1] - pair[0] > 50 ) { return find_reasonable_bound( array_between_bounds( pair[0], pair[1], 10 ) ) } else { return pair; } } )
.then( pair => { if( pair[1] - pair[0] > 50 ) { return find_reasonable_bound( array_between_bounds( pair[0], pair[1], 10 ) ) } else { return pair; } } )
.then( pair => {
options_map.lastpage = pair[1];
document.getElementById( 'browse10' ).href += "?lastpage=" + options_map.lastpage; // Add last-page indicator to Browse Images link
document.getElementById( 'browse5' ).href += "?lastpage=" + options_map.lastpage; // ... and the 5-pages-at-once link.
document.getElementById( 'browse1' ).href += "?lastpage=" + options_map.lastpage; // ... and the 1-page-at-onces link.
document.getElementById( 'exp10' ).href += "?lastpage=" + options_map.lastpage; // ... and this fetch-every-post link.
document.getElementById( 'exp5' ).href += "?lastpage=" + options_map.lastpage; // ... and this fetch-every-post link.
document.getElementById( 'exp1' ).href += "?lastpage=" + options_map.lastpage; // ... and this fetch-every-post link.
start_scraping_button();
} );
}
else { // If we're given the highest page by the URL, just use that
start_scraping_button();
}
// Add "Scrape" button to the page. This will grab images and links from many pages and list them page-by-page.
function start_scraping_button() {
if( options_map.grabrange ) { // If we're only grabbing a 1000-page block from a huge-ass tumblr:
mydiv.innerHTML += " This will grab 1000 pages starting at " + options_map.grabrange + ".
";
} else { // If we really are describing the last page:
mydiv.innerHTML += " Last page is " + options_map.lastpage + " or lower.
";
}
if( options_map.lastpage > 1500 && !options_map.grabrange ) { // If we need to link to 1000-page blocks, and aren't currently inside one:
for( var x = 1; x < options_map.lastpage; x += 1000 ) { // For every 1000 pages...
var decade_url = window.location.href + "?grabrange=" + x + "?lastpage=" + options_map.lastpage;
mydiv.innerHTML += "Pages " + x + "-" + (x+999) + " "; // ... link a range of 1000 pages.
}
}
// Add button to scrape every page, one after another.
// Buttons within GreaseMonkey are a huge pain in the ass. I stole this from stackoverflow.com/questions/6480082/ - thanks, Brock Adams.
var button = document.createElement ('div');
button.innerHTML = '';
button.setAttribute ( 'id', 'scrape_button' ); // I'm really not sure why this id and the above HTML id aren't the same property.
document.body.appendChild ( button ); // Add button (at the end is fine)
document.getElementById ("myButton").addEventListener ( "click", scrape_all_pages, false ); // Activate button - when clicked, it triggers scrape_all_pages()
if( options_map.autostart ) { document.getElementById ("myButton").click(); } // Getting tired of clicking on every reload - debug-ish
if( options_map.lastpage <= 26 ) { document.getElementById ("myButton").click(); } // Automatic fetch (original behavior!) for a single round
}
}
function scrape_all_pages() { // Example code implies that this function /can/ take a parameter via the event listener, but I'm not sure how.
var button = document.getElementById( "scrape_button" ); // First, remove the button. There's no reason it should be clickable twice.
button.parentNode.removeChild( button ); // The DOM can only remove elements from a higher level. "Elements can't commit suicide, but infanticide is permitted."
mydiv.innerHTML += "Scraping page:
"; // This makes it easier to view progress,
// Create divs for all pages' content, allowing asynchronous AJAX fetches
var x = 1;
var div_end_page = options_map.lastpage;
if( !isNaN( options_map.grabrange ) ) { // If grabbing 1000 pages from the middle of 10,000, don't create 0..10,000 divs
x = options_map.grabrange;
div_end_page = x + 1000; // Should be +999, but whatever, no harm in tiny overshoot
}
for( ; x <= div_end_page; x++ ) {
var siteurl = site_and_tags + "/page/" + x;
if( options_map.usemobile ) { siteurl += "/mobile"; } // If ?usemobile is flagged, scrape the mobile version.
if( x == 1 && options_map.usemobile ) { siteurl = site_and_tags + "/mobile"; } // Hacky fix for redirect from example.tumblr.com/page/1/anything -> example.tumblr.com
var new_div = document.createElement( 'div' );
new_div.id = '' + x;
document.body.appendChild( new_div );
}
// Fetch all pages with content on them
var page_counter_div = document.getElementById( 'pagecounter' ); // Probably minor, but over thousands of laggy page updates, I'll take any optimization.
pagecounter.innerHTML = "" + 1;
var begin_page = 1;
var end_page = options_map.lastpage;
if( !isNaN( options_map.grabrange ) ) { // If a range is defined, grab only 1000 pages starting there
begin_page = options_map.grabrange;
end_page = options_map.grabrange + 999; // NOT plus 1000. Stop making that mistake. First page + 999 = 1000 total.
if( end_page > options_map.lastpage ) { end_page = options_map.lastpage; } // Kludge
document.title += " " + (parseInt( begin_page / 1000 ) + 1); // Change page title to indicate which block of pages we're saving
}
// Generate array of URL/pagenum pair-arrays
url_index_array = new Array;
for( var x = begin_page; x <= end_page; x++ ) {
var siteurl = site_and_tags + "/page/" + x;
if( options_map.usemobile ) { siteurl += "/mobile"; } // If ?usemobile is flagged, scrape the mobile version. No theme shenanigans... but also no photosets. Sigh.
if( x == 1 && options_map.usemobile ) { siteurl = site_and_tags + "/mobile"; } // Hacky fix for redirect from example.tumblr.com/page/1/anything -> example.tumblr.com
url_index_array.push( [siteurl, x] );
}
// Fetch, scrape, and display all URLs. Uses promises to work in parallel and promise.all to limit speed and memory (mostly for reliability's sake).
// Consider privileging first page with single-element fetch, to increase apparent responsiveness. Doherty threshold for frustration is 400ms.
var simultaneous_fetches = 25;
var chain = Promise.resolve(0); // Empty promise so we can use "then"
var order_array = [1]; // We want to show the first page immediately, and this is a callback rat's-nest, so let's make an array of how many pages to take each round
for( var x = 1; x < url_index_array.length; x += simultaneous_fetches ) { // E.g. [1, simultaneous_fetchs, s_f, s_f, s_f, whatever's left]
if( url_index_array.length - x > simultaneous_fetches ) { order_array.push( simultaneous_fetches ); } else { order_array.push( url_index_array.length - x ); }
}
order_array.forEach( (how_many) => {
chain = chain.then( s => {
var subarray = url_index_array.splice( 0, how_many ); // Shift a reasonable number of elements into separate array, for partial array.map
return Promise.all( subarray.map( page =>
Promise.all( [ fetch( page[0] ).then( s => s.text() ), page[1], page[0] ] ) // Return [ body of page, page number, page URL ]
) )
} )
.then( responses => responses.map( s => { // Scrape URLs for links and images, display on page
var pagenum = s[1];
var page_url = s[2];
var url_array = soft_scrape_page_promise( s[0] ) // Surprise, this is a promise now
.then( urls => {
// Sort #link URLs to appear first, because we don't do that in soft-scrape anymore
urls.sort( (a,b) => -a.indexOf( "#link" ) ); // Strings containing "#link" go before others - return +1 if not found in 'a.' Should be stable.
// Print URLs so DownThemAll (or similar) can grab them
var bulk_string = " " + page_url + " "; // A digest, so we can update innerHTML just once per div
// DEBUG-ish - on theory that 1000-page-tall scraping/rendering fucks my VRAM
if( options_map.smalltext ) { bulk_string = "
" + bulk_string; } // If ?smalltext flag is set, render text unusably small, for esoteric reasons
urls.forEach( (value,index,array) => {
if( options_map.plaintext ) {
bulk_string += value + ' ';
} else {
bulk_string += '' + value + ' ';
}
} )
document.getElementById( '' + pagenum ).innerHTML = bulk_string;
if( parseInt( pagecounter.innerHTML ) < pagenum ) { pagecounter.innerHTML = "" + pagenum; } // Increment pagecounter (where sensible)
} );
} )
)
} )
chain = chain.then( s => {
document.getElementById( 'afterpagecounter' ).innerHTML = "Done. Use DownThemAll (or a similar plugin) to grab all these links.";
// DEBUG: divulge contents of page_dupe_hash to check for common tags
// Ugh, I'm going to have to turn this from an associative array into an array-of-arrays if I want to sort it.
let tag_overview = " " + "Tag overview: " + " ";
let score_tag_list = new Array; // This will hold an array of arrays so we can sort this associative array by its values. Wheee.
for( let url in page_dupe_hash ) {
if( url.indexOf( '/tagged/' ) > 0 // If it's a tag URL...
&& page_dupe_hash[ url ] > 1 // and non-unique...
&& url.indexOf( '/page/' ) < 0 // and not a page link...
&& url.indexOf( '?og' ) < 0 // and not an opengraph link...
&& url.indexOf( '?ezas' ) < 0 // and not this script, wtf...
) { // So if it's a TAG, in other words...
score_tag_list.push( [ page_dupe_hash[ url ], url ] ); // ... store [ number of times seen, tag URL ] for sorting.
}
}
score_tag_list.sort( (a,b) => a[0] > b[0] ); // Ascending order, now - most common tags at the very bottom, for easier access
score_tag_list.map( pair => {
var this_tag = pair[1].split('/').pop(); // e.g. example.tumblr.com/tagged/my-art -> my-art
var scrape_link = options_url( {find: '/tagged/'+this_tag, lastpage: false, grabrange: false, autostart: true} ); // Direct link to ?scrapewholesite for e.g. /tagged/my-art
tag_overview += " " + pair[0] + " posts:\t" + "" + pair[1] + "";
} )
document.body.innerHTML += tag_overview;
} )
}
// ------------------------------------ Multi-page scraper with embedded images ------------------------------------ //
function scrape_tumblr_pages() {
// Grab an empty page so that duplicate-removal hides whatever junk is on every single page
// This is DEBUG-ish. It might be slow, barring caching. It might not work due to asynchrony. It could block actual content thanks to 'my best posts' sidebars.
if( isNaN( parseInt( options_map.startpage ) ) || options_map.startpage <= 1 ) { options_map.startpage = 1; } // Sanity check
mydiv.innerHTML += " " + html_previous_next_navigation() + " ";
document.getElementById("bottom_controls_div").innerHTML += " " + html_page_count_navigation() + " " + html_previous_next_navigation();
mydiv.innerHTML += " " + html_ezastumblrscrape_options() + " ";
mydiv.innerHTML += " " +image_size_options();
// Fill an array with the page URLs to be scraped (and create per-page divs while we're at it)
var pages = new Array( parseInt( options_map.pagesatonce ) )
.fill( parseInt( options_map.startpage ) )
.map( (value,index) => value+index );
pages.forEach( pagenum => {
mydiv.innerHTML += "
Page " + pagenum + "
";
} )
pages.map( pagenum => {
var siteurl = site_and_tags + "/page/" + pagenum; // example.tumblr.com/page/startpage, startpage+1, startpage+2, etc.
if( options_map.usemobile ) { siteurl += "/mobile"; } // If ?usemobile is flagged, scrape mobile version. No theme shenanigans... but also no photosets. Sigh.
if( pagenum == 1 && options_map.usemobile ) { siteurl = site_and_tags + "/mobile"; } // Hacky fix for redirect from example.tumblr.com/page/1/anything -> example.tumblr.com
fetch( siteurl ).then( response => response.text() ).then( text => {
document.getElementById( pagenum ).innerHTML += "fetched " // Immediately indicate the fetch happened.
+ "" + siteurl + " "; // Link to page. Useful for viewing things in-situ... and debugging.
// For some asinine reason, 'return url_array' causes 'Permission denied to access property "then".' So fake it with ugly nesting.
soft_scrape_page_promise( text )
.then( url_array => {
var div_digest = ""; // Instead of updating each div's HTML for every image, we'll lump it into one string and update the page once per div.
var video_array = new Array;
var outlink_array = new Array;
var inlink_array = new Array;
url_array.forEach( (value,index,array) => { // Shift videos and links to separate arrays, blank out those URLs in url_array
if( value.indexOf( '#video' ) > 0 ) { video_array.push( value ); array[index] = '' }
if( value.indexOf( '#offsite' ) > 0 ) { outlink_array.push( value ); array[index] = '' }
if( value.indexOf( '#local' ) > 0 ) { inlink_array.push( value ); array[index] = '' }
} );
url_array = url_array.filter( url => url === "" ? false : true ); // Remove empty elements from url_array
// Display video links, if there are any
video_array.forEach( value => {div_digest += "Video: " + value + " "; } )
// Display page links if the ?showlinks flag is enabled
if( options_map.showlinks ) {
div_digest += "Outgoing links: ";
outlink_array.forEach( (value,index) => { div_digest += "O" + (index+1) + " " } );
div_digest += " " + "Same-Tumblr links: ";
inlink_array.forEach( (value,index) => { div_digest += "T" + (index+1) + " " } );
div_digest += " ";
}
// Embed high-res images to be seen, clicked, and saved
url_array.forEach( image_url => {
// Embed images (linked to themselves) and link to photosets
if( image_url.indexOf( "#photoset#" ) > 0 ) { // Before the first image in a photoset, print the photoset link.
var photoset_url = image_url.split( "#" ).pop();
// URL is like tumblr.com/image#photoset#http://tumblr.com/photoset_iframe - separate past last hash... t.
div_digest += " Set:";
}
div_digest += ""
+ " ";
} )
div_digest += " (End of " + siteurl + ")"; // Another link to the page, because I'm tired of scrolling back up.
document.getElementById( pagenum ).innerHTML += div_digest;
} ) // End of 'then( url_array => { } )'
} ) // End of 'then( text => { } )'
} ) // End of 'pages.map( pagenum => { } )'
}
// ------------------------------------ Whole-site scraper based on post-by-post method ------------------------------------ //
function scrape_sitemap() {
// Fetch /sitemap.xml
// Process that file for other xml links (sitemap1.xml, sitemap2.xml, etc.)
// Fetch those other links
// Process those other xml documents (upper range is 500+, so not all at once naively) for /post links
// Sort completed /post list (or not, they should be in some order within the XML) and start fetching / displaying post+image pairs
// Remember, promise.all doesn't care what you return, just that you return something.
// Can I do .all instead of .then?
// This is compartmentalized enough by sitemapX files - maybe just loop?
// Maybe just spaghettify so that .then( map promise.all ).then( map promise.all ) sequence is comprehensible to human eyes.
// Sitemap.xml grab returns array of URLs.
// Grabbing each of those URLs returns an array of array of URLs.
// Grabbing each of -those- URLs returns an array of... objects?... remembering each URL and its scraped contents.
// Aaand then you have to display it all.
var all_posts = new Array;
var base_site = window.location.protocol + "//" + window.location.hostname; // e.g. http://example.tumblr.com
fetch( base_site + '/sitemap.xml' ) // Grab text-like file
.then( r => r.text() ) // Get text from HTTP response
.then( t => { // Extract links
let sitemap_list = t.split( '' ); // Break at each location declaration
sitemap_list.shift(); // Ditch first element, which is garbage
sitemap_list = sitemap_list.map( e => e.split( '' )[0] ); // Break off each past location undeclaration
// sitemap_list should now contain [ http://example.tumblr.com/sitemap1.xml, http://example.tumblr.com/sitemap2.xml, etc. ]
console.log( sitemap_list );
return sitemap_list;
} )
// then map_list filter( indexOf '/sitemap' ) // filter out URLs without '/sitemap' in them
.then( map_list => { // Given a list of sitemap1, sitemap2, etc. URLs
// Promise.all goes somewhere in here
map_list.map( a_sitemap => { // For each URL
fetch( a_sitemap ) // Fetch each URL
.then( mr => mr.text() ) // Turn response into text
.then( post_map => { // Given that text:
var post_list = post_map.split( '' ); // Split on location declaration
post_list.shift(); // Shift off useless first element
post_list = post_list.map( post_url => post_url.split( '' )[0] ) // Break off each past location undeclaration
// post_list should now contain about 500 /post URLs in an array
console.log( post_list );
// return post_list;
all_posts = all_posts.concat( post_list );
} )
.then( posts => { // Given a list of /post URLs
} )
} )
} )
// .then filter / sort / gradually fetch-and-scrape everything in all_posts
}
// ------------------------------------ Post-by-post scraper with embedded images ------------------------------------ //
// Scrape each page for /post/ links, scrape each /post/ for content, display in-order with less callback hell
// New layout & new scrape method - not required to be compatible with previous functions
function new_embedded_display() {
if( isNaN( parseInt( options_map.startpage ) ) || options_map.startpage <= 1 ) { options_map.startpage = 1; }
mydiv.innerHTML += "
";
// Links out from this mode - scrapewholesite, original mode, maybe other crap
mydiv.innerHTML += "This mode is under development and subject to change.";
// mydiv.innerHTML += " - Return to original image browser" + " " + " ";
mydiv.innerHTML += " " + html_ezastumblrscrape_options() + "
";
// Messy inline function for toggling page breaks - they're optional because we have post permalinks now
mydiv.innerHTML += "Toggle page breaks
";
mydiv.innerHTML += ""; // Empty span for things to be placed after.
posts_placed.push( 0 ); // Because fuck special cases.
// Scrape some pages
for( let x = options_map.startpage; x < options_map.startpage + options_map.pagesatonce; x++ ) {
fetch( site_and_tags + "/page/" + x ).then( r => r.text() ).then( text => {
scrape_by_posts( text, x );
} )
}
}
// Take the HTML from a /page, fetch the /post links, display images
// Probably ought to be despaghettified and combined with the above function, but I was fighting callback hell -hard- after the last major version
// Alternately, split it even further and do some .then( do_this ).then( do_that ) kinda stuff above.
function scrape_by_posts( html_copy, page_number ) {
let posts = links_from_page( html_copy ); // Get links on page
posts = posts.filter( link => { return link.indexOf( '/post/' ) > 0 && link.indexOf( '/photoset' ) < 0; } ); // Keep /post links but not photoset iframes
posts = posts.map( link => { return link.replace( '#notes', '' ); } ); // post/1234 is the same as /post/1234#notes
posts = posts.filter( link => link.indexOf( window.location.host ) > 0 ); // Same-origin filter. Not necessary, but it unclutters the console. Fuckin' CORS.
if( page_number != 1 ) { posts = posts.filter( novelty_filter ); } // Attempt to remove posts linked on every page, e.g. commission info. Suffers a race condition.
posts = remove_duplicates( posts ); // De-dupe
// 'posts' now contains an array of /post URLs
// Display link and linebreak before first post on this page
let first_id = posts.map( u => parseInt( u.split( '/' )[4] ) ).sort( ).pop(); // Grab ID from its place in each URL, sort accordingly, take the top one
let page_link = " Page " + page_number + "";
if( posts.length == 0 ) { first_id = 1; page_link += " - No images found."; } // Handle empty pages with dummy content. Out of order, but whatever.
page_link += "
";
display_post( page_link, first_id + 0.5 ); // +/- on the ID will change with /chrono, once that matters
posts.map( link => {
/*
if( options_map[ 'embedded' ] ) { // Embedded-view mode - different URLs, presumably different subdomain
// Arg, except embedded links are most useful when themes are fucked. This scrape method still relies on /post links from /pages!
// We can't fetch /page links from embed.tumblr.com because of cross-origin bullshit.
}
*/
fetch( link ).then( r => r.text() ).then( text => {
let sublinks = links_from_page( text );
sublinks = sublinks.filter( s => { return s.indexOf( '.jpg' ) > 0 || s.indexOf( '.jpeg' ) > 0 || s.indexOf( '.png' ) > 0 || s.indexOf( '.gif' ) > 0; } );
sublinks = sublinks.filter( tumblr_blacklist_filter ); // Remove avatars and crap
sublinks = sublinks.map( image_standardizer ); // Clean up semi-dupes (e.g. same image in different sizes -> same URL)
sublinks = sublinks.filter( novelty_filter ); // Global duplicate remover
// Oh. Photosets sort of just... work? That might not be reliable; DownThemAll acts like it can't see the iframes on some themes.
// Yep, they're there. Gonna be hard to notice if/when they fail. Oh well, "not all images are guaranteed to appear."
// Videos will still be weird. (But it does grab their preview thumbnails.)
// Wait, can I filter reblogs here? E.g. with a ?noreblogs flag, and then checking if any given post has via/source links. Hmm. Might be easier in /mobile pages.
// Get ID from post URL, e.g. http//example.tumblr.com/post/12345/title => 12345
let post_id = parseInt( link.split( '/' )[4] ); // 12345 as a NUMBER, not a string, doofus
if( sublinks.length > 0 ) { // If this post has images we're displaying -
let this_post = new String;
sublinks.map( url => {
this_post += '';
this_post += '';
this_post += '';
this_post += 'Permalink ';
} )
display_post( this_post, post_id );
}
} )
} )
}
// Place content on page in descending order according to post ID number
// Consider rejiggering the old scrape method to use this. Move to 'universal' section if so. Alter or spin off to link posts instead?
// Turns out I never implemented ?chrono or ?reverse, so nevermind that for now.
// Remember to set options_map.chrono if ?find contains /chrono or whatever.
function display_post( content, post_id ) {
let this_node = document.createElement( "span" );
this_node.innerHTML = content;
this_node.id = post_id
// Find lower-numbered node than post_id
let target_id = posts_placed.filter( n => n <= post_id ).sort( ).pop(); // Take the highest number less than (or equal to) post_id
if( options_map.find.indexOf( '/chrono' ) > 0 ) {
target_id = posts_placed.filter( n => n <= post_id ).sort( ).shift(); // Take the... fuck... lowest? What am I doing again?
// Fuuuck, this is really inconsistent. Nevermind the looney-toons syntax I used here, =>n<=.
// Screw it, use the old scraper for now.
}
let target_node = document.getElementById( target_id );
// http://stackoverflow.com/questions/4793604/how-to-do-insert-after-in-javascript-without-using-a-library
target_node.parentNode.insertBefore( this_node, target_node ); // Insert our span after the lower-ID node
posts_placed.push( post_id ); // Remember that we added this ID
// No return value
}
// Return ascending or descending order depending on "chrono" setting
// function post_order_sort( a, b )
// ------------------------------------ HTML-returning functions for duplication prevention ------------------------------------ //
// Return HTML for standard Previous / Next controls (<<< Previous - Next >>>)
function html_previous_next_navigation() {
let prev_next_controls = "";
if( options_map.startpage > 1 ) {
prev_next_controls += "<<< Previous - ";
}
prev_next_controls += "Next >>>";
return prev_next_controls;
}
// Return HTML for pages-at-once versions of previous/next page navigation controls (<<< 10, 5, 1 - 1, 5, 10 >>>)
function html_page_count_navigation() {
let prev_next_controls = "";
if( options_map.startpage > 1 ) { // <<< 10, 5, 1 -
prev_next_controls += "<<< ";
prev_next_controls += " 1, ";
prev_next_controls += " 5, ";
prev_next_controls += " 10 - ";
}
prev_next_controls += " 10, ";
prev_next_controls += " 5, ";
prev_next_controls += " 1 - ";
prev_next_controls += ">>>";
return prev_next_controls;
}
// Return HTML for image-size options (changes via CSS or via URL parameters)
function image_size_options() {
var html_string = "Immediate: \t"; // Change class to instantly resize images, temporarily
html_string += "Original image sizes - ";
html_string += "Snap columns - ";
html_string += "Snap rows - ";
html_string += "Fit width - ";
html_string += "Fit height - ";
html_string += "Fit both
";
html_string += "Persistent: \t"; // Reload page with different image mode that will stick for previous/next pages
html_string += "Original image sizes - "; // This is the CSS default, so any other value works
html_string += "Snap columns - ";
html_string += "Snap rows - ";
html_string += "Fit width - ";
html_string += "Fit height - ";
html_string += "Fit both";
return html_string;
}
// Return links to other parts of Eza's Tumblr Scrape functionality, possibly excluding whatever you're currently doing
// Switch to full-size images - Toggle image size - Show one page at once - Scrape whole Tumblr - (Experimental fetch-every-post image browser)
// This mode is under development and subject to change. - Return to original image browser
function html_ezastumblrscrape_options() {
let html_string = "";
// "You are browsing" text? Tell people where they are and what they're looking at.
html_string += "Scrape whole Tumblr - ";
html_string += "Browse images - "; // Default mode; so any value works
html_string += "(Experimental fetch-every-post image browser) ";
return html_string;
}
function error_function( url ) {
// This clunky function looks for a lower-res image if the high-res version doesn't exist.
// Surprisingly, this does still matter. E.g. http://66.media.tumblr.com/ba99a55896a14a2e083cec076f159956/tumblr_inline_nyuc77wUR01ryfvr9_500.gif
// This might mismatch _100 images and _250 links because of that self-erasing clause... but it's super rare, so meh.
let on_error = 'if(this.src.indexOf("_raw")>0){this.src=this.src.replace("_raw","_1280").replace("//media","//66.media");}'; // Swap _raw for 1280, add CDN number
on_error += 'else if(this.src.indexOf("_1280")>0){this.src=this.src.replace("_1280","_500");}'; // Swap 1280 for 500
on_error += 'else if(this.src.indexOf("_500")>0){this.src=this.src.replace("_500","_400");}'; // Or swap 500 for 400
on_error += 'else if(this.src.indexOf("_400")>0){this.src=this.src.replace("_400","_250");}'; // Or swap 400 for 250
on_error += 'else{this.src=this.src.replace("_250","_100");this.onerror=null;}'; // Or swap 250 for 100, then give up
on_error += 'document.getElementById("' + encodeURI( url ) + '").href=this.src;'; // Link the image to itself, regardless of size
return on_error;
}
// ------------------------------------ Universal page-scraping function (and other helper functions) ------------------------------------ //
// Add URLs from a 'blank' page to page_dupe_hash (without just calling soft_scrape_page_promise and ignoring its results)
function exclude_content_example( url ) {
fetch( url ).then( r => r.text() ).then( text => {
let links = links_from_page( text );
links = links.map( image_standardizer );
links = links.filter( novelty_filter );
} )
// No return value
}
// Spaghetti to reduce redundancy: given a page's text, return a list of URLs.
function links_from_page( html_copy ) {
// Cut off the page at the "More you might like" / "Related posts" footer, on themes that have one
html_copy = html_copy.split( '="related-posts' ).shift();
let http_array = html_copy.split( /['="']http/ ); // Regex split on anything that looks like a source or href declaration
http_array.shift(); // Ditch first element, which is just etc.
http_array = http_array.map( s => { // Theoretically parallel .map instead of maybe-linear .forEach or low-level for() loop
s = s.split( /['<>"']/ )[0]; // Terminate each element (split on any terminator, take first subelement)
s = s.replace( /\\/g, '' ); // Remove escaping backslashes (e.g. http\/\/ -> http//)
if( s.indexOf( "%3A%2F%2F" ) > -1 ) { s = decodeURIComponent( s ); } // What is with all the http%3A%2F%2F URLs?
return "http" + s; // Oh yeah, add http back in (regex eats it)
} ) // http_array now contains an array of strings that should be URLs
let post_array = html_copy.split( /['="']\/post/ ); // Regex split on anything that defines looks similar to a src="/post" link
post_array.shift(); // Ditch first element, which is just etc.
post_array = post_array.map( s => { // Theoretically parallel .map instead of maybe-linear .forEach or low-level for() loop
s = s.split( /['<>"']/ )[0]; // Terminate each element (split on any terminator, take first subelement)
return window.location.protocol + "//" + window.location.hostname + "/post" + s; // Oh yeah, add /post back in (regex eats it)
} ) // post_array now contains an array of strings that should be photoset URLs
http_array = http_array.concat( post_array ); // Photosets are out of order again. Blar.
return http_array;
}
// Filter: Return false for typical Tumblr nonsense (JS, avatars, RSS, etc.)
function tumblr_blacklist_filter( url ) {
if( url.indexOf( "/reblog/" ) > 0 ||
url.indexOf( "/tagged/" ) > 0 || // Might get removed so the script can track and report tag use. Stupid art tags like 'my-draws' or 'art-poop' are a pain to find.
url.indexOf( ".tumblr.com/avatar_" ) > 0 ||
url.indexOf( ".tumblr.com/image/" ) > 0 ||
url.indexOf( ".tumblr.com/rss" ) > 0 ||
url.indexOf( "srvcs.tumblr.com" ) > 0 ||
url.indexOf( "assets.tumblr.com" ) > 0 ||
url.indexOf( "schema.org" ) > 0 ||
url.indexOf( ".js" ) > 0 ||
url.indexOf( ".css" ) > 0 ||
url.indexOf( "twitter.com/intent" ) > 0 || // Weirdly common now
url.indexOf( "ezastumblrscrape" ) > 0 ) // Somehow this script is running on pages being fetched, inserting a link. Okay. Sure.
{ return false } else { return true }
}
// Return standard canonical URL for various resizes of Tumblr images - size of _1280, single CDN
function image_standardizer( url ) {
// Some lower-size images are automatically resized. We'll change the URL to the maximum size just in case, and Tumblr will provide the highest resolution.
// Replace all resizes with _1280 versions. Nearly all _1280 URLs resolve to highest-resolution versions now, so we don't need to e.g. handle GIFs separately.
// Oh hey, Tumblr now has _raw for a no-bullshit as-large-as-possible setting.
// _raw only works without the CDN - so //media.tumblr yes, but //66.media.tumblr no. This complicates things.
// Does //media and _raw always work? No, of course not. So we still need on_error.
url = url.replace( "_1280.", "_raw." ).replace( "_540.", "_raw." ).replace( "_500.", "_raw." ).replace( "_400.", "_raw." ).replace( "_250.", "_raw." ).replace( "_100.", "_raw." );
// henrythehangman.tumblr.com has doubled images from /image posts in ?scrapemode=everypost. Lots of _1280.jpg?.jpg nonsense.
// Is that typical for tumblrs with this theme? It's one of those annoying magnifying-glass-on-hover deals. If it's just that one weird fetish site, remove this later.
url = url.split('?')[0]; // Ditch anything past the first question mark, if one exists
// Standardize media subdomain / CDN subsubdomain, to prevent duplicates and fix _1280 vs _raw complications.
if( url.indexOf( '.media.tumblr.com/' ) > 0 ) {
let url_parts = url.split( '/' )
url_parts[2] = 'media.tumblr.com';
url = url_parts.join( '/' ).replace( 'http:', 'https:' );
}
// Change back to _1280 & CDN for ?scrapewholesite (which does no testing). _raw is unreliable.
if( options_map.scrapemode == 'scrapewholesite' ) {
url = url.replace( "_raw.", "_1280." ).replace( '//media', '//66.media' );
}
return url;
}
// Remove duplicates from an array (from an iterable?) - returns de-duped array
// Credit to http://stackoverflow.com/questions/9229645/remove-duplicates-from-javascript-array for hash-based string method
function remove_duplicates( list ) {
let seen = {};
list = list.filter( function( item ) {
return seen.hasOwnProperty( item ) ? false : ( seen[ item ] = true );
} );
return list;
}
// Filter: Return true ONCE for any given string.
// Global duplicate remover - return false for items found in page_dupe_hash, otherwise add new items to it and return true
// Now also counts instances of each non-unique argument
function novelty_filter( url ) {
// return page_dupe_hash.hasOwnProperty( url ) ? false : ( page_dupe_hash[ url ] = true );
url = url.toLowerCase(); // Debug-ish, mostly for "tag overview." URLs can be case-sensitive but collisions will be rare. "Not all images are guaranteed to appear."
if( page_dupe_hash.hasOwnProperty( url ) ) {
page_dupe_hash[ url ] += 1;
return false;
} else {
page_dupe_hash[ url ] = 1;
return true;
}
}
// Given the bare HTML of a Tumblr page, return an array of Promises for image/video/link URLs
function soft_scrape_page_promise( html_copy ) {
// Linear portion:
let http_array = links_from_page( html_copy ); // Split bare HTML into link and image sources
http_array.filter( url => url.indexOf( '/tagged/' ) > 0 ).filter( novelty_filter ); // Track tags for statistics, before the blacklist removes them
http_array = http_array.filter( tumblr_blacklist_filter ); // Blacklist filter for URLs - typical garbage
function is_an_image( url ) {
// Whitelist URLs with image file extensions or Tumblr iframe indicators
var image_link = false;
if( url.indexOf( ".gif" ) > 0 ) { image_link = true; }
if( url.indexOf( ".jpg" ) > 0 ) { image_link = true; }
if( url.indexOf( ".jpeg" ) > 0 ) { image_link = true; }
if( url.indexOf( ".png" ) > 0 ) { image_link = true; }
if( url.indexOf( "/photoset_iframe" ) > 0 ) { image_link = true; }
if( url.indexOf( ".tumblr.com/video/" ) > 0 ) { image_link = true; }
return image_link;
}
// Separate the images
http_array = http_array.map( url => {
if( is_an_image( url ) ) { // If it's an image, get rid of any Tumblr variability about resolution or CDNs, to avoid duplicates with nonmatching URLs
return image_standardizer( url );
} else { // Else if not an image
if( url.indexOf( window.location.host ) > 0 ) { url += "#local" } else { url += "#offsite" } // Mark in-domain vs. out-of-domain URLs.
if( options_map.imagesonly ) { return ""; } // ?imagesonly to skip links on ?scrapewholesite
return url + "#link";
}
} )
.filter( n => { // Remove all empty strings, where "empty" can involve a lot of #gratuitous #tags.
if( n.split("#")[0] === "" ) { return false } else { return true }
} );
http_array = remove_duplicates( http_array ); // Remove duplicates within the list
http_array = http_array.filter( novelty_filter ); // Remove duplicates throughout the page
// Should this be skipped on scrapewholesite? Might be slowing things down.
// Async portion:
// Return promise that resolves to list of URLs, including fetched videos and photoset sub-images
return Promise.all( http_array.map( s => {
if( s.indexOf( '/photoset_iframe' ) > 0 ) { // If this URL is a photoset, return a promise for an array of URLs
return fetch( s ).then( r => r.text() ).then( text => { // Fetch URL, get body text from response
var photos = text.split( 'href="' ); // Isolate photoset elements from href= declarations
photos.shift(); // Get rid of first element because it's everything before the first "href"
photos = photos.map( p => p.split( '"' )[0] + "#photoset" ); // Tag all photoset images as such, just because
photos[0] += "#" + s; // Tag first image in set with photoset URL so browse mode can link to it
return photos;
} )
}
else if ( s.indexOf( '.tumblr.com/video/' ) > 0 ) { // Else if this URL is an embedded video, return a Tumblr-standard URL for the bare video file
var subdomain = s.split( '/' ); // E.g. https://www.tumblr.com/video/examplename/123456/500/ -> https,,www.tumblr.com,video,examplename,123456,500
var video_post = window.location.protocol + "//" + subdomain[4] + ".tumblr.com/post/" + subdomain[5] + "/";
// e.g. http://examplename.tumblr.com/post/123456/ - note window.location.protocol vs. subdomain[0], maintaining http/https locally
return fetch( video_post ).then( r => r.text() ).then( text => {
if( text.indexOf( 'og:image' ) > 0 ) { // property="og:image" content="http://67.media.tumblr.com/tumblr_123456_frame1.jpg" --> tumblr_123456_frame1.jpg
var video_name = text.split( 'og:image' )[1].split( 'media.tumblr.com' )[1].split( '"' )[0].split( '/' ).pop();
} else if( text.indexOf( 'poster=' ) > 0 ) { // poster='https://31.media.tumblr.com/tumblr_nuzyxqeJNh1rjoppl_frame1.jpg'
var video_name = text.split( "poster='" )[1].split( 'media.tumblr.com' )[1].split( "'" )[0].split( '/' ).pop(); // Bandaid solution. Tumblr just sucks.
} else {
return video_post + '#video'; // Current methods miss the whole page if these splits miss, so fuck it, just return -something.-
}
// tumblr_abcdef12345_frame1.jpg -> tumblr_abcdef12345.mp4
video_name = "tumblr_" + video_name.split( '_' )[1] + ".mp4#video";
video_name = "https://vt.tumblr.com/" + video_name; // Standard Tumblr-wide video server
return video_name; // Should be e.g. https://vt.tumblr.com/tumblr_abcdef12345.mp4
} )
}
return Promise.resolve( [s] ); // Else if this URL is singular, return a single element... resolved as a promise for Promise.all, in an array for Array.concat. Whee.
} ) )
.then( nested_array => { // Given the Promise.all'd array of resolved URLs and URL-arrays
return [].concat.apply( [], nested_array ); // Concatenate array of arrays - apply turns array into comma-separated list, concat turns CSL of arrays into a single array
} )
}
// Returns a URL with all the options_map options in ?key=value format - optionally allowing changes to options in the returned URL
// Valid uses:
// options_url() -> all current settings, no changes
// options_url( "name", number ) -> ?name=number
// options_url( "name", true ) -> ?name
// options_url( {name:number} ) -> ?name=number
// options_url( {name:number, other:true} ) -> ?name=number?other
// Note that simply passing "name" will remove ?name, not add it, because the value will evaluate false. I should probably change this? Eh, { key } without :value causes errors.
function options_url( key, value ) {
var copy_map = new Object();
for( var i in options_map ) { copy_map[ i ] = options_map[ i ]; }
// In any sensible language, this would read "copy_map = object_map." Javascript genuinely does not know how to copy objects. Fuck's sake.
if( typeof key === 'string' ) { // the parameters are optional. just calling options_url() will return e.g. example.tumblr.com/archive?ezastumblrscrape?startpage=1
if( !value ) { value = false; } // if there's no value then use false
copy_map[ key ] = value; // change this key, so we can e.g. link to example.tumblr.com/archive?ezastumblrscrape?startpage=2
}
else if( typeof key === 'object' ) { // If we're passed a hashmap
for( var i in key ) {
if( ! key[ i ] ) { key[ i ] = false; } // Turn any false evaluation into an explicit boolean - this might not be necessary
copy_map[ i ] = key[ i ]; // Press key-object values onto copy_map-object values
}
}
// Construct URL from options
var base_site = window.location.href.substring( 0, window.location.href.indexOf( "?" ) ); // should include /archive, but if not, it still works on most pages
for( var k in copy_map ) { // JS maps are weird. We're actually setting attributes of a generic object. So map[ "thumbnails" ] is the same as map.thumbnails.
if( copy_map[ k ] ) { // Unless the value is False, print a ?key=value pair.
base_site += "?" + k;
if( copy_map[ k ] !== true ) { base_site += "=" + copy_map[ k ]; } // If the value is boolean True, just print the value as a flag.
}
}
return base_site;
}