https://hiphoplife.com.tr üzerindeki tüm albümleri/singleları çekmek için bişi. Kahrolsun arşivci kişiliğim. 🤔

hiphoplife-crawler.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-

# TODO: Mega downloader

import json
import requests
from bs4 import BeautifulSoup
import re
import codecs

class HLCrawler():
	
	def getMagaLink(self,url):
		r = requests.get(url)
		m = re.search("window.location = '(.*?)'", r.text)
		redirect = m.group(1)
		r = requests.get(redirect)
		return r.url

	def crawlPagination(self,url):
		r = requests.get(url)
		soup = BeautifulSoup(r.text, 'html.parser')
		try:
			tracks = soup.findAll("div", { "class" : "remositoryfileblock" })
			for track in tracks:
				title = track.findAll("a")[0].text
				downloadUrlHL = track.findAll("a", href=True)[1]["href"]
				downloadUrlHL = self.getMagaLink(downloadUrlHL)
				self.PAGES[self.pagesKey] = {'title': title, 'url':downloadUrlHL}

				print("{0} Bulundu -> URL -> {1}".format(title.encode('utf-8').strip(),downloadUrlHL))
				self.pagesKey += 1
		except IndexError:
			 print("Dead. \n")

	
	def __init__(self):
		self.URL = "https://www.hiphoplife.com.tr/dosyalar/Mp3/orderby,2/page,{0}/";
		self.TRACKS = {}
		self.PAGES = {}
		self.MAX_PAGE = 196

		self.pagesKey = 0

		for x in xrange(1,self.MAX_PAGE + 1):
			print("\n{0}. sayfa crawl ediliyor.\n".format(x))
			self.crawlPagination(self.URL.format(x))

if __name__ == "__main__":
	HLCrawler()