Last active
December 27, 2021 21:31
-
-
Save diagprov/27cde8ec94505afc136327da6c9c0372 to your computer and use it in GitHub Desktop.
Extract all data from Goodreads
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
$tbl = document.getElementById("books"); | |
var bl = new Array(); | |
for (let i = 1; i < $tbl.rows.length; i++) { | |
$row = $tbl.rows[i] | |
$htitlerow = $row.getElementsByClassName("field title")[0] | |
$htitleanchor = $htitlerow.getElementsByClassName("value")[0].childElements()[0] | |
$title = $htitleanchor.text | |
$hauthorrow = $row.getElementsByClassName("field author")[0] | |
$hauthoranchor = $hauthorrow.getElementsByClassName("value")[0].childElements()[0] | |
$author = $hauthoranchor.text | |
$hisbnrow = $row.getElementsByClassName("field isbn13")[0] | |
$hisbn = $hisbnrow.getElementsByClassName("value")[0] | |
$isbn13 = "" | |
if($hisbn != null) { | |
$isbn13 = $hisbn.textContent | |
} | |
var entry = { | |
"Title": $title, | |
"Author": $author, | |
"ISBN13": $isbn13 | |
}; | |
bl.push(entry); | |
} | |
console.log(bl); |
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
import csv | |
import json | |
import yaml | |
def isbn_filter(obj): | |
return obj.get("ISBN13").replace(" ", "").replace("\n", "") | |
def author_filter(obj): | |
last, first = obj.get("Author").split(",") | |
last = last.replace(" ", "") | |
first = first.replace(" ", "") | |
return (last, first) | |
def title_filter(obj): | |
cleaned = obj.get("Title").split("\n")[1:3] | |
title = cleaned[0].strip(" ") | |
series = "" | |
num = "" | |
try: | |
series, num = cleaned[1].strip(" ").strip("()").split(", #") | |
except ValueError: | |
try: | |
series, num = cleaned[1].strip(" ").strip("()").split(" #") | |
except ValueError: | |
try: | |
cleaner = cleaned[1].strip(" ") | |
if cleaner != "" and ";" in cleaner: | |
cleanrr = cleaner.split(";")[0].strip("(") | |
series, num = cleanrr.split(", #") | |
else: | |
series = "" | |
num = "" | |
except ValueError: | |
series = "" | |
num = "" | |
return (title, series, num) | |
rawbooks = b'' | |
with open("allbooks.json", "rb+") as f: | |
rawbooks = f.read() | |
bookju = json.loads(rawbooks.decode("utf-8")) | |
books = [] | |
for o in bookju: | |
ISBN13 = isbn_filter(o) | |
AuthorLast, AuthorFirst = author_filter(o) | |
Title, Series, Number = title_filter(o) | |
newobj = { | |
"ISBN13": ISBN13, | |
"AuthorLast": AuthorLast, | |
"AuthorFirst": AuthorFirst, | |
"Title": Title, | |
"Series": Series, | |
"Number": Number} | |
books.append(newobj) | |
books_encoded = yaml.dump(books) | |
with open("allbooks.yml", "wb") as f: | |
f.write(books_encoded.encode("utf-8")) | |
keys = books[0].keys() | |
with open("allbooks.csv", 'w') as f: | |
w = csv.DictWriter(f, fieldnames=list(keys), dialect='excel') | |
w.writeheader() | |
for obj in books: | |
w.writerow(obj) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment