Last active
March 20, 2016 16:14
-
-
Save sfan5/1cec90d7dfda457e0065 to your computer and use it in GitHub Desktop.
Download all your fav'ed @catgirls_bot pictures and their original images (where possible)
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
// Go to https://twitter.com/favorites and scoll all the way until there are no more fav'd @catgirls_bot tweets | |
// maybe like this: | |
// window.temp=function(){window.scrollTo(0,document.body.scrollHeight);setTimeout(window.temp,750)};window.temp() | |
// window.temp=function(){}; // stop like this | |
var _q = document.getElementById('stream-items-id'); | |
var _i; | |
var _o = []; | |
for(_i = 0; _i < _q.children.length; _i++) { | |
var _e = _q.children[_i]; | |
if(_e.children[0].getAttribute('data-screen-name') == 'catgirls_bot') { | |
var _a = _e.children[0].getAttribute('data-tweet-id'); | |
_e = _e.children[0].children[1]; | |
var _l = _e.children[1].children[0].children[0].getAttribute('data-expanded-url'); | |
var _p = _e.children[2].children[0].children[0].children[0].getAttribute('data-image-url') + ":large"; | |
_o.push({id: _a, link: _l, picture: _p}); | |
} | |
} | |
var _w = window.open(); | |
if(_w) { | |
_w.document.open(); | |
_w.document.write('<h1>Copy this and save it into <i>favs.json</i></h1>'); | |
_w.document.write('<pre>'); | |
_w.document.write(JSON.stringify(_o, null, ' ')); | |
_w.document.write('</pre>'); | |
_w.document.close(); | |
} |
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
#!/usr/bin/env python3 | |
import sys | |
import urllib.request | |
import re | |
import getopt | |
################## | |
PHPSESSID = "your_phpsessid_here" | |
################## | |
def gopt(opts, n): | |
v = None | |
for opt in opts: | |
if opt[0] == n: | |
v = opt[1] | |
return v | |
r_image = re.compile(r'<img alt="[^"]+" width="[0-9]+" height="[0-9]+" data-src="([a-z0-9:/.\-_]+)" class="original-image">') | |
r_manga = re.compile(r'<a href="member_illust\.php\?mode=manga&illust_id=[0-9]+"') | |
r_mangaimage = re.compile(r'<img src="([a-z0-9:/.\-_]+)"') | |
try: | |
opts, args = getopt.getopt(sys.argv[1:], "o:q", ['no-manga']) | |
except getopt.GetoptError as e: | |
print(str(e)) | |
exit(1) | |
if len(args) < 1: | |
print("Usage: %s [-q] [--no-manga] [-o FILENAME] <pixiv ID> [2nd argument]" % sys.argv[0]) | |
print("The 2nd argument is usually the page number.") | |
exit(1) | |
def urlopen(url, headers): | |
h = { | |
"User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:38.0) Gecko/20100101 Firefox/38.0", | |
"Cookie": "PHPSESSID=%s; p_ab_id=4; a_type=0" % PHPSESSID | |
} | |
h.update(headers) | |
r = urllib.request.Request(url, headers=h) | |
return urllib.request.urlopen(r) | |
pixiv_id = int(args[0]) | |
arg2 = "" if len(args) < 2 else args[1].strip() | |
page = "http://www.pixiv.net/member_illust.php?mode=medium&illust_id=%d" % pixiv_id | |
r = urlopen(page, {}) | |
data = r.read().decode("utf-8", "ignore") | |
r.close() | |
if r_manga.search(data): # Manga | |
if ('--no-manga', '') in opts: | |
if not ('-q', '') in opts: | |
print("Illustration is a manga and --no-manga given, exiting.") | |
exit(1) | |
if arg2 == "": | |
if not ('-q', '') in opts: | |
print("Illustration is a manga but no page number given, downloading first page by default") | |
print("Set the page number by giving the script a second argument") | |
page_no = 0 | |
else: | |
page_no = int(arg2) - 1 | |
page = "http://www.pixiv.net/member_illust.php?mode=manga_big&illust_id=%d&page=%d" % (pixiv_id, page_no) | |
r = urlopen(page, {}) | |
data = r.read().decode("utf-8", "ignore") | |
r.close() | |
m = r_mangaimage.search(data) | |
if not m: | |
print("Couldn't find URL") | |
exit(1) | |
imgurl = m.group(1) | |
else: # Single image | |
m = r_image.search(data) | |
if not m: | |
print("Couldn't find URL") | |
exit(1) | |
imgurl = m.group(1) | |
if not ('-q', '') in opts: | |
print("Downloading %s..." % imgurl) | |
filename = imgurl.split("/")[-1] | |
if gopt(opts, '-o'): | |
filename = gopt(opts, '-o') + "." + filename.split(".")[-1] | |
f = open(filename, "wb") | |
r = urlopen(imgurl, {"Referer": page}) | |
while True: | |
data = r.read(256 * 1024) # 256 KiB | |
if not data: | |
break | |
f.write(data) | |
r.close() | |
f.close() | |
if not ('-q', '') in opts: | |
print("Saved work %d as %s" % (pixiv_id, filename)) |
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
#!/usr/bin/env python3 | |
import json | |
import urllib | |
import urllib.request | |
import re | |
import subprocess | |
import multiprocessing | |
import time | |
infile = "favs.json" | |
outdir = "/tmp/twpics/" | |
nworkers_twit = 4 | |
nworkers_orig = 5 | |
r_ext = re.compile(r'\.([a-z]+):large$') | |
r_pixiv = re.compile(r'^http:\/\/www\.pixiv\.net\/member_illust\.php\?mode=medium&illust_id=([0-9]+)$') | |
r_danbooru = re.compile(r'^https?:\/\/danbooru\.donmai\.us\/posts\/[0-9]+$') | |
r_yandere = re.compile(r'^https?:\/\/yande\.re\/post\/show\/[0-9]+$') | |
r_yandere_orig = re.compile(r'<a class="original-file-changed" id="highres" href="https:\/\/files\.yande\.re\/image\/([0-9a-z]{32})\/[^"]+\.([a-z]{,3})">') | |
def urlopen(url, headers={}): | |
h = {} | |
h["User-Agent"] = "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:38.0) Gecko/20100101 Firefox/38.0" | |
h.update(headers) | |
r = urllib.request.Request(url, headers=h) | |
return urllib.request.urlopen(r) | |
def fdcopy(fp1, fp2): | |
while True: | |
data = fp1.read(1024 * 1024) | |
if not data: | |
return | |
fp2.write(data) | |
def download_original(link, filebase): | |
if r_pixiv.search(link): | |
pixiv_id = r_pixiv.search(link).group(1) | |
p = subprocess.Popen(["/path/to/pixivdl.py", "-q", "--no-manga", "-o", filebase, pixiv_id]) | |
p.wait() | |
return (p.returncode == 0) | |
elif r_danbooru.search(link): | |
s = urlopen(link + ".json") | |
data = json.loads(s.read().decode("utf-8", "ignore")) | |
s.close() | |
if "file_url" not in data: # deleted image | |
return False | |
link = data["file_url"] | |
s = urlopen("http://danbooru.donmai.us" + link) | |
f = open(filebase + "." + link.split(".")[-1], "wb") | |
fdcopy(s, f) | |
s.close() | |
f.close() | |
return True | |
elif r_yandere.search(link): | |
s = urlopen(link) | |
data = s.read().decode("utf-8", "ignore") | |
s.close() | |
m = r_yandere_orig.search(data) | |
if not m: | |
return False | |
s = urlopen("https://files.yande.re/image/%s/a.%s" % m.groups()) | |
f = open(filebase + "." + m.group(2), "wb") | |
fdcopy(s, f) | |
s.close() | |
f.close() | |
return True | |
else: | |
return False | |
def worker_twit(queue): | |
# Downloads twitter image | |
for e in iter(queue.get, "STOP"): | |
print("worker_twit: " + e["id"]) | |
picext = r_ext.search(e["picture"]).group(1) | |
s = urlopen(e["picture"].replace(":large", ":orig")) | |
f = open(outdir + e["id"] + "." + picext, "wb") | |
fdcopy(s, f) | |
s.close() | |
f.close() | |
def worker_orig(queue): | |
# Tries to download orignal image, otherwise notes URL in .txt file | |
for e in iter(queue.get, "STOP"): | |
print("worker_orig: " + e["id"]) | |
if not download_original(e["link"], outdir + e["id"] + "_o"): | |
f = open(outdir + e["id"] + "_o.txt", "w") | |
f.write(e["link"]) | |
f.write("\n") | |
f.close() | |
f = open(infile, "r") | |
data = json.load(f) | |
f.close() | |
queue_twit = multiprocessing.SimpleQueue() | |
queue_orig = multiprocessing.SimpleQueue() | |
for i in range(nworkers_twit): | |
multiprocessing.Process(target=worker_twit, args=(queue_twit, )).start() | |
for i in range(nworkers_orig): | |
multiprocessing.Process(target=worker_orig, args=(queue_orig, )).start() | |
for e in data: | |
queue_twit.put(e) | |
if not e['link'] is None: | |
queue_orig.put(e) | |
for i in range(nworkers_twit): | |
queue_twit.put("STOP") | |
for i in range(nworkers_orig): | |
queue_orig.put("STOP") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment