User:Pedro Sá Couto/Prototyping 3rd: Difference between revisions
Line 12: | Line 12: | ||
</gallery> | </gallery> | ||
[[File:Blur01.png|thumbnail]] | |||
[[File:Blur02.png|thumbnail]] | |||
[[File:verso00.png|thumbnail]] | |||
[[File:verso01.png|thumbnail]] | |||
<source lang="python"> | <source lang="python"> | ||
#SCRIPT GOES HERE WHEN FINISHED | #SCRIPT GOES HERE WHEN FINISHED |
Revision as of 15:42, 25 May 2019
Watermarks, downloading, deleting
https://pad.xpub.nl/p/IFL_2018-05-13
JSOR (Ithaka Harbors, Inc) publishers
- download an article from http://jstor.org/ from within school
- search for watermarks on the PDF
- look for some leads in https://sourceforge.net/p/pdfedit/mailman/message/27874955/ — https://github.com/kanzure/pdfparanoia/issues?utf8=%E2%9C%93&q=jstor
#SCRIPT GOES HERE WHEN FINISHED
Verso Books
- Create an account in https://www.versobooks.com/
- Download book as epub, a free one will do, for instance https://www.versobooks.com/books/2772-verso-2017-mixtape
- search for watermarks on the EPUB
- Look at the Institute for Biblio-Immunology -- First Communique: https://pastebin.com/raw/E1xgCUmb for more leads. https://www.booxtream.com/
Tesseract, OCR, Book scan
<script type="text/javascript">
//store all class 'ocr_line' in 'lines'
var lines = document.querySelectorAll(".ocr_line");
//loop through each element in 'lines'
for (var i = 0; i < lines.length; i++){
var line = lines[i];
console.log(line.title)
//split the content of 'title' every space and store the list in 'parts'
var parts = line.title.split(" ");
console.log(parts);
// width and height starts from the side
var left = parseInt(parts[1], 10);
var top = parseInt(parts[2], 10);
var width = (parseInt(parts[3], 10) - left);
var height = (parseInt(parts[4], 10) - top);
// create a style element with the content selected from the list 'parts'
line.style = "position: absolute; left: " + parts[1] + "px; top: " + parts[2] + "px; width: " + width + "px; height: " + height + "px; border: 5px solid lightblue";
var words = line.querySelectorAll(".ocrx_word");
for (var e = 0; e < words.length; e++){
var span = words[e];
console.log(span.title)
var parts = span.title.split(" ");
console.log(parts);
var wleft = parseInt(parts[1], 10);
var wtop = parseInt(parts[2], 10);
var wwidth = (parseInt(parts[3], 10) - wleft);
var wheight = (parseInt(parts[4], 10) - wtop);
span.style = "position: absolute; left: " + (wleft - left) + "px; top: " + (wtop - top) + "px; width: " + wwidth + "px; height: " + wheight + "px; border: 2px solid purple";
}
}