4chan file/webm downloader/pipe it to mpv etc

4chanwebm.py

import json, re, sys, os,time
from urllib.request import urlopen as u
'''
it searches for all files, not only webms. (jpg, png, gif, webm).
usage examples:

Searches for 'Ricardo Thread' in the board wsg and print all file links.
Useful for piping to mpv and watching them. (e.g.)
4chanwebm.py board 'bla bla' --print_links | xargs mpv
      
    python 4chanwebm.py wsg 'Ricado Thread' --print_links

Searches for 'trap thread' in board gif and saves and files to current directory.

    python 4chanwebm.py gif  'trap thread' --save

Prints all threads in the board /a/.

    python 4chanwebm.py a --catalog
    
'''
if "--no-colors" in sys.argv:
	class bc:
		 HEADER = ''
		 OKBLUE = ''
		 OKGREEN = ''
		 WARNING = ''
		 FAIL = ''
		 ENDC = ''
		 BOLD = ''
		 UNDERLINE = ''
else:
	class bc:
		 HEADER = '\033[95m'
		 OKBLUE = '\033[38;5;192m'
		 BLACKFG = '\033[38;5;236m'
		 OKGREEN = '\033[92m'
		 WARNING = '\033[93m'
		 FAIL = '\033[91m'
		 ENDC = '\033[0m'
		 BOLD = '\033[1m'
		 UNDERLINE = '\033[4m'



#board = str(''.join(re.findall("\/(\w+)\/", url)))


def cleanStr(raw_str):
	space2 = re.sub('<br><br>', '<br>', raw_str)
	space = re.sub('<br>', '\n', space2)
	cleanExpr = re.compile('<.*?>')
	tagsclean = re.sub(cleanExpr, '', space)
	gts = re.sub("\&gt\;", '>', tagsclean)
	return gts


def printTitleCom(catal):
	for page in range(len(catal)):
		for thread in range(len(catal[page]["threads"])):
			bread = catal[page]["threads"][thread]
			try:
				print(bc.OKBLUE+bc.BLACKFG+"*"+bc.ENDC+bread['sub'])
			except KeyError:
				comment = cleanStr(bread['com'])
				print(comment[:75])
	
def print_shit(bread):
	try:
		print(bread['sub'])
	except KeyError:
		pass
	try:
		comm = cleanStr(bread['com'])
		print(bc.OKBLUE+"COM:", comm.format(3,5)+bc.ENDC)
	except KeyError:
		pass
#	com = (comm[:200] + '...') if len(bread['com']) > 200 else bread['com']
	# print(bc.OKBLUE+bc.BLACKFG+"PAGE: %d\nTHREAD: %d" % (page,thread)+bc.ENDC)
	print("FILES:", bread['images'])
	print("REPLIES:", bread['replies'])
	print("REPLIES:", bread['filename'])
	print("NUM:", bread['no'])


# Searches in thread title for string
def searchBread(catal, string):
	for page in range(len(catal)):
		for thread in range(len(catal[page]["threads"])):
			bread = catal[page]["threads"][thread]
			try:
				if re.search(string, cleanStr(bread['sub'])):
					print_shit(bread,page,thread)
					return bread['no']
			except KeyError:
				continue

def searchBreadCom(catal, string):
    found = False
    for page in range(len(catal)):
            for thread in range(len(catal[page]["threads"])):
                    searchBreadCom.bread = catal[page]["threads"][thread]
#			print("iterating in", page, "thread", thread)
                    try:
                            if re.search(string, searchBreadCom.bread['com']):
#					print_shit(bread,page,thread)
#					print("FOUND SUB")
                                    return searchBreadCom.bread['no']

                    except KeyError:
                            pass
                    try:
                            if re.search(string, searchBreadCom.bread['sub']):
#					print_shit(bread,page,thread)
#					print("FOUND COM")
                                    return searchBreadCom.bread['no']

                    except KeyError:
                            continue


def saveShit(trUrl):
	skipped = 0
	bread = json.loads(u(trUrl).read())
##	print(bread["posts"][0]['semantic_url'])
	llist = ["https://i.4cdn.org/"+board+"/"+str(post['tim'])+post['ext']
		for post in bread["posts"]
			if post.get("ext")]


	if "--print_links" in sys.argv:
		print('\n'.join(llist))
		sys.exit()


	for dex,i in enumerate(llist, start=1):
		fn = re.sub("https://i.4cdn.org\/(\w+)\/", "", i)
		if fn in os.listdir():
			skipped = skipped +1 
			print(" %d/%d SKIPPED"%(skipped,len(llist)),end="\r")
#			sys.stdout.write("\033[F")
			time.sleep(0.05)
			continue
		print(bread["posts"][0]['semantic_url'],fn, dex, "OUT OF", len(llist)-1)
		b = u(i).read()
		with open(fn, 'wb') as f:
			f.write(b)
#	print('\n'.join(llist))

if "--save" in sys.argv:
	board = sys.argv[1]
	url = "https://a.4cdn.org/" + sys.argv[1] + "/catalog.json"

	catal = json.loads(u(url).read())
	if "-xom" in sys.argv:
		cc = searchBreadCom(catal, sys.argv[2])
	else:
		cc = searchBreadCom(catal, sys.argv[2])
	if cc == None:
		print("Nothing found")
		sys.exit()
	trString = "https://a.4cdn.org/%s/thread/%s.json" %(board,cc)
	saveShit(trString)


else:
    board = sys.argv[1]
    url = "https://a.4cdn.org/" + sys.argv[1] + "/catalog.json"

    catal = json.loads(u(url).read())

    if "--catalog" in sys.argv:
            printTitleCom(catal)
            sys.exit()
#	if "-xom" in sys.argv:
    # print("Searching comment in", sys.argv[2])
    cc = searchBreadCom(catal, sys.argv[2])
#	else:
#		print("")
#		cc = searchBread(catal, sys.argv[2])
    if cc == None:
        print("Nothing found")
        sys.exit()
    trString = "https://a.4cdn.org/%s/thread/%s.json" %(board,cc)
    # print(trString)
    # print(len(sys.argv))
#	printAll(catal)
    if "--print_links" in sys.argv:
            saveShit(trString)
            print("")
    if len(sys.argv) < 4:
        print_shit(searchBreadCom.bread)