request with session

Crawler/Crawler.py

@@ -2,59 +2,38 @@ import requests
 import urllib
 import bs4
 import re
+import os
 
 from .Setting import Setting
 from .ProxyHandler import ProxyHandler
 from .Logger import Logger
+from .Util import Util
+from .DataType import PageLink, TorrentFile
 
-
-class PageLink:
-	def __init__(self):
-		self.title = ''
-		self.episode = ''
-		self.url = ''
-
-	def __init__(self, title, episode, url):
-		self.title = title
-		self.episode = episode
-		self.url = url
-
-	def __str__(self):
-		return '{{ {}({}): {} }}'.format(self.title, self.episode, self.url)
-
-	def __repr__(self):
-		return str(self)
-
-
-class TorrentFile:
-	def __init__(self):
-		self.title = ''
-		self.episode = ''
-		self.file_name = ''
-		self.url = ''
-
-	def __init__(self, title, episode, file_name, url):
-		self.title = title
-		self.file_name = file_name
-		self.episode = episode
-		self.url = url
-
-	def __str__(self):
-		return '{{ {}({}): {}({}) }}'.format(self.title, self.episode, self.file_name, self.url)
-
-	def __repr__(self):
-		return str(self)
+from .WorkerTorrentKim import WorkerTorrentKim
+from .WorkerTfreeca import WorkerTfreeca
+from .WorkerTocops import  WorkerTocops
 
 
 class Crawler:
 	def __init__(self):
 		self.setting = Setting()
+		self.session = requests.session()
 		self.proxy_handler = ProxyHandler()
+		self.worker = None
+
 		if len(self.setting.settings['urls']) > 0:
 			urlinfo = urllib.parse.urlparse(self.setting.settings['urls'][0])
 			top_url = urllib.parse.urlunparse((urlinfo.scheme, urlinfo.netloc, '', '', '', ''))
 			self.proxy_handler.check_url = top_url
 
+		if 'torrentkim' in top_url:
+			self.worker = WorkerTorrentKim()
+		elif 'tfreeca' in top_url:
+			self.worker = WorkerTfreeca()
+		elif 'tcorea' in top_url:
+			self.worker = WorkerTocops()
+
 	@staticmethod
 	def print_log(files):
 		f = open('output/log.txt', 'at')
@@ -66,16 +45,15 @@ class Crawler:
 		headers = {
 			'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.115 Safari/537.36',
 			'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
-			'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.3',
-			'Accept-Encoding': 'gzip, deflate, br',
-			'Accept-Language': 'ko-KR,ko;q=0.8,en-US;q=0.6,en;q=0.4',
+			'Accept-Charset': 'utf-8,euc-kr;q=0.7,*;q=0.3',
+			'Accept-Language': 'ko-KR,ko;q=0.9,en-US;q=0.8,en;q=0.7',
 			'Connection': 'keep-alive',
 		}
 
 		proxy = self.proxy_handler.get_proxy()
 		while True:
 			try:
-				resp = requests.get(url, proxies=proxy, headers=headers, timeout=3)
+				resp = self.session.get(url, proxies=proxy, headers=headers, timeout=3)
 			except Exception as e:
 				self.proxy_handler.set_proxy_dead(proxy)
 				proxy = self.proxy_handler.get_proxy()
@@ -96,41 +74,10 @@ class Crawler:
 		resp = self.request_get(url)
 		soup = bs4.BeautifulSoup(resp.content.decode('utf8'), 'lxml')
 
-		re_title = re.compile('|'.join(['(?P<key'+str(i)+'>'+video['keyword']+')' for i, video in enumerate(self.setting.settings['video'])]), re.I)
+		re_title = re.compile('|'.join(['(?P<key' + str(i) + '>' + video['keyword'] + ')' for i, video in enumerate(self.setting.settings['video'])]), re.I)
 		re_episode = re.compile(r'[ .,]E([0-9]+)[ .,]', re.I)
 
-		links = []
-		tables = soup.select('table.board_list')
-		trs = tables[0].select('tr')
-		for tr in trs[1:]:
-			tds = tr.select('td.subject')
-			title = tds[0].text.strip()
-			link = tds[0].select('a')[0].attrs['href']
-
-			title_match = re_title.search(title)
-			if not title_match:
-				continue
-
-			ep_match = re_episode.search(title)
-			if not ep_match:
-				continue
-
-			title_idx = int(title_match.lastgroup[3:])
-			video = self.setting.settings['video'][title_idx]
-			ep = int(ep_match.group(1))
-
-			if ep <= video['ignore_ep_under']:
-				Logger.log('    {}({}) is ignored (previous episode than ep{})'.format(video['title'], ep, video['ignore_ep_under']))
-				continue
-			elif ep in self.setting.downloaded[video['title']]:
-				Logger.log('    {}({}) is ignored (already downloaded)'.format(video['title'], ep))
-				continue
-
-			link = urllib.parse.urljoin(url, link)
-			links.append(PageLink(video['title'], ep, link))
-
-			Logger.log('   found content page : {}({}), {}'.format(video['title'], ep, link))
-
+		links = self.worker.crawl_list(url, soup, re_title, re_episode, self.setting)
 		return links
 
 	def crawl_downlink(self, page_link):
@@ -139,28 +86,7 @@ class Crawler:
 		resp = self.request_get(page_link.url)
 		soup = bs4.BeautifulSoup(resp.content.decode('utf8'), 'lxml')
 
-		links = []
-		file_table = soup.select('table#file_table')
-		a_tags = file_table[0].select('a')
-		torrent_links = [a for a in a_tags if '.torrent' in a.text]
-		smi_links = [a for a in a_tags if '.smi' in a.text]
-
-		for link in torrent_links:
-			file_name = link.text.strip()
-			sub_url = link.attrs['href']
-			url = urllib.parse.urljoin(page_link.url, sub_url)
-			links.append(TorrentFile(page_link.title, page_link.episode, file_name, url))
-
-			Logger.log('    found download link : {}({})'.format(file_name, url))
-
-		for link in smi_links:
-			file_name = link.text.strip()
-			sub_url = link.attrs['href']
-			url = urllib.parse.urljoin(link.url, sub_url)
-			links.append(TorrentFile(page_link.title, page_link.episode, file_name, url))
-
-			Logger.log('    found download link : {}({})'.format(file_name, url))
-
+		links = self.worker.crawl_downlink(page_link, soup)
 		return links
 
 	def download_files(self, file_link):
@@ -171,15 +97,14 @@ class Crawler:
 
 		try:
 			resp = self.request_get(file_link.url)
-			file_name = re.findall("filename=\"(.+)\"", resp.headers['content-disposition'])
-			file_name = urllib.parse.unquote(file_name[0])
+			file_name = file_link.file_name
 			with open(self.setting.settings['download_path'] + file_name, 'wb') as f:
 				f.write(resp.content)
 
 			self.setting.downloaded[file_link.title].append(file_link.episode)
 			self.setting.save()
 
-			Logger.log("downloaded {}".format(file_link.file_name))
+			Logger.log("downloaded {}".format(file_name))
 
 		except Exception as e:
 			Logger.log(e)
@@ -201,6 +126,28 @@ class Crawler:
 			self.download_files(file)
 
 	def crawl(self):
+		if Util.get_free_space() < 4*1024*1024:
+			Logger.log('Disk space is less than 4GB. Aborted')
+			return
+
+		# self.test()
+
 		Logger.log('Crawling start')
 		self.crawl_torrent()
 		Logger.log('Crawling finished')
+
+
+class Sorter:
+	@staticmethod
+	def move_files():
+		setting = Setting()
+		if not 'file_download_path' in setting.settings or not 'file_move_path' in setting.settings:
+			return
+
+		file_list = os.listdir(setting.settings['file_download_path'])
+		for filename in file_list:
+			for video in setting.settings['video']:
+				if video['title'] in filename:
+					old_path = os.path.join(setting.settings['file_download_path'], filename)
+					new_path = os.path.join(setting.settings['file_move_path'], video['title'] + '/' + filename)
+					os.rename(old_path, new_path)

Crawler/DataType.py

@@ -0,0 +1,36 @@
+class PageLink:
+	def __init__(self):
+		self.title = ''
+		self.episode = ''
+		self.url = ''
+
+	def __init__(self, title, episode, url):
+		self.title = title
+		self.episode = episode
+		self.url = url
+
+	def __str__(self):
+		return '{{ {}({}): {} }}'.format(self.title, self.episode, self.url)
+
+	def __repr__(self):
+		return str(self)
+
+
+class TorrentFile:
+	def __init__(self):
+		self.title = ''
+		self.episode = ''
+		self.file_name = ''
+		self.url = ''
+
+	def __init__(self, title, episode, file_name, url):
+		self.title = title
+		self.file_name = file_name
+		self.episode = episode
+		self.url = url
+
+	def __str__(self):
+		return '{{ {}({}): {}({}) }}'.format(self.title, self.episode, self.file_name, self.url)
+
+	def __repr__(self):
+		return str(self)

Crawler/ProxyHandler.py

@@ -3,9 +3,10 @@ import pickle
 import requests
 import bs4
 import concurrent.futures
+import time
 
 from .Logger import Logger
-
+from .Util import Util
 
 class ProxyHandler:
 	PROXY_FILE_NAME = 'temp/proxy.bin'
@@ -29,7 +30,7 @@ class ProxyHandler:
 	def check_proxy_all(self, proxies, check_url):
 		Logger.log('checking proxies for {}'.format(check_url))
 
-		worker_cnt = 64
+		worker_cnt = 16
 		pool = concurrent.futures.ThreadPoolExecutor(worker_cnt)
 		[pool.submit(self.check_proxy, proxy, check_url) for proxy in proxies]
 		pool.shutdown()
@@ -64,12 +65,51 @@ class ProxyHandler:
 				}
 			)
 
+		resp = requests.get('https://www.socks-proxy.net')
+		soup = bs4.BeautifulSoup(resp.text, 'lxml')
+		table = soup.select('table.table')
+		trs = table[0].select('tr')
+		for tr in trs[1:]:
+			tds = tr.select('td')
+			if len(tds) < 2:
+				continue
+
+			ip, port = tds[0].text, tds[1].text
+			proxies.append(
+				{
+					'alive': True,
+					'http': '{}:{}'.format(ip, port),
+					'https': '{}:{}'.format(ip, port),
+				}
+			)
+
+		resp = requests.get('https://www.sslproxies.org')
+		soup = bs4.BeautifulSoup(resp.text, 'lxml')
+		table = soup.select('table.table')
+		trs = table[0].select('tr')
+		for tr in trs[1:]:
+			tds = tr.select('td')
+			if len(tds) < 2:
+				continue
+
+			ip, port = tds[0].text, tds[1].text
+			proxies.append(
+				{
+					'alive': True,
+					'http': '{}:{}'.format(ip, port),
+					'https': '{}:{}'.format(ip, port),
+				}
+			)
+
+		# print(proxies)
 		self.check_proxy_all(proxies, self.check_url)
+		# print(proxies)
 		alive_proxies = [proxy for proxy in proxies if proxy['alive']]
 		Logger.log('proxies checking end: available : {}'.format(len(alive_proxies)))
 
-		with open(self.PROXY_FILE_NAME, 'wb') as f:
-			pickle.dump(alive_proxies, f)
+		if Util.get_free_space() >= 1024:
+			with open(self.PROXY_FILE_NAME, 'wb') as f:
+				pickle.dump(alive_proxies, f)
 
 		return alive_proxies
 
@@ -77,8 +117,16 @@ class ProxyHandler:
 		if len(self.proxies) <= 0:
 			if self.has_file():
 				self.proxies = self.load_proxy()
-			else:
+				self.proxies = [proxy for proxy in self.proxies if proxy['alive']]
+				
+		if len(self.proxies) <= 0:
+			while True:
 				self.proxies = self.crawl_proxy()
+				if len(self.proxies) > 0:
+					break
+				else:
+					Logger.log('there is no available proxy. sleep 10secs..')
+					time.sleep(10)
 
 		for proxy in self.proxies:
 			if proxy['alive']:
@@ -89,7 +137,7 @@ class ProxyHandler:
 	def set_proxy_dead(self, proxy):
 		proxy['alive'] = False
 		for proxy in self.proxies:
-			if proxy['alive']:
+			if proxy['alive'] and Util.get_free_space() >= 1024:
 				with open(self.PROXY_FILE_NAME, 'wb') as f:
 					pickle.dump(self.proxies, f)
 				return

Crawler/Setting.py

@@ -2,7 +2,7 @@ import yaml
 import os
 
 from .Logger import Logger
-
+from .Util import Util
 
 class Setting:
 	SETTING_FILE = 'conf/settings.yml'
@@ -51,8 +51,8 @@ class Setting:
 			if 'download_path' not in self.settings:
 				self.settings['download_path'] = '.'
 
-			if self.settings['download_path'][-1] != '\\':
-				self.settings['download_path'] += '\\'
+			if self.settings['download_path'][-1] != '/':
+				self.settings['download_path'] += '/'
 
 			if not os.path.exists(self.settings['download_path']):
 				try:
@@ -61,6 +61,20 @@ class Setting:
 					Logger.log(e)
 					exit()
 
+			if 'download_path' in self.settings and self.settings['file_download_path'][-1] != '/':
+				self.settings['file_download_path'] += '/'
+
+			if 'file_move_path' in self.settings:
+				if self.settings['file_move_path'][-1] != '/':
+					self.settings['file_move_path'] += '/'
+
+				if not os.path.exists(self.settings['file_move_path']):
+					try:
+						os.makedirs(self.settings['file_move_path'])
+					except Exception as e:
+						Logger.log(e)
+						exit()
+
 			video['keyword'] += self.settings['keyword_append']
 
 	def load_downloaded(self):
@@ -117,6 +131,9 @@ class Setting:
 			yaml.dump(downloaded_ex, outfile, allow_unicode=True)
 
 	def save(self):
+		if Util.get_free_space() < 1024:
+			return
+
 		with open(self.DOWNLOADED_FILE, 'w', encoding='utf-8') as outfile:
 			yaml.dump(self.downloaded, outfile, allow_unicode=True)
 		pass

Crawler/Util.py

@@ -0,0 +1,13 @@
+import subprocess
+import platform
+
+class Util:
+	@staticmethod
+	def get_free_space():
+		if platform.system() == 'Linux':
+			df = subprocess.Popen(["df", "/"], stdout=subprocess.PIPE)
+			output = df.communicate()[0]
+			device, size, used, available, percent, mountpoint = str(output).split("\\n")[1].split()
+		else:
+			available = 1024*1024*1024*1024;
+		return int(available)

Crawler/WorkerTfreeca.py

@@ -0,0 +1,78 @@
+import requests
+import urllib
+import bs4
+import re
+import os
+
+from .Setting import Setting
+from .ProxyHandler import ProxyHandler
+from .Logger import Logger
+from .Util import Util
+from .DataType import PageLink, TorrentFile
+
+
+class WorkerTfreeca:
+	def crawl_list(self, top_url, soup, re_title, re_episode, setting):
+
+		links = []
+		tables = soup.select('table.b_list')
+		trs = tables[0].select('tr')
+		for tr in trs[1:]:
+			tds = tr.select('td.subject')
+			if len(tds) < 1:
+				continue
+
+			title = tds[0].text.strip()
+			link = tds[0].select('a')[1].attrs['href']
+
+			title_match = re_title.search(title)
+			if not title_match:
+				continue
+
+			ep_match = re_episode.search(title)
+			if not ep_match:
+				continue
+
+			title_idx = int(title_match.lastgroup[3:])
+			video = setting.settings['video'][title_idx]
+			ep = int(ep_match.group(1))
+
+			if ep <= video['ignore_ep_under']:
+				Logger.log('    {}({}) is ignored (previous episode than ep{})'.format(video['title'], ep, video['ignore_ep_under']))
+				continue
+			elif ep in setting.downloaded[video['title']]:
+				Logger.log('    {}({}) is ignored (already downloaded)'.format(video['title'], ep))
+				continue
+
+			link = urllib.parse.urljoin(top_url, link)
+			links.append(PageLink(video['title'], ep, link))
+
+			Logger.log('   found content page : {}({}), {}'.format(video['title'], ep, link))
+
+		return links
+
+	def crawl_downlink(self, page_link, soup):
+
+		links = []
+		file_table = soup.select('table#file_table')
+		a_tags = file_table[0].select('a')
+		torrent_links = [a for a in a_tags if '.torrent' in a.text]
+		smi_links = [a for a in a_tags if '.smi' in a.text]
+
+		for link in torrent_links:
+			file_name = link.text.strip()
+			sub_url = link.attrs['href']
+			url = urllib.parse.urljoin(page_link.url, sub_url)
+			links.append(TorrentFile(page_link.title, page_link.episode, file_name, url))
+
+			Logger.log('    found download link : {}({})'.format(file_name, url))
+
+		for link in smi_links:
+			file_name = link.text.strip()
+			sub_url = link.attrs['href']
+			url = urllib.parse.urljoin(link.url, sub_url)
+			links.append(TorrentFile(page_link.title, page_link.episode, file_name, url))
+
+			Logger.log('    found download link : {}({})'.format(file_name, url))
+
+		return links

Crawler/WorkerTocops.py

@@ -0,0 +1,74 @@
+import requests
+import urllib
+import bs4
+import re
+import os
+
+from .Setting import Setting
+from .ProxyHandler import ProxyHandler
+from .Logger import Logger
+from .Util import Util
+from .DataType import PageLink, TorrentFile
+
+class WorkerTocops:
+	def crawl_list(self, top_url, soup, re_title, re_episode, setting):
+
+		links = []
+		tables = soup.select('table.board_list')
+		trs = tables[0].select('tr')
+		for tr in trs[1:]:
+			tds = tr.select('td.subject')
+			if len(tds) < 1:
+				continue
+
+			title = tds[0].text.strip()
+			link = tds[0].select('a')[0].attrs['href']
+
+			title_match = re_title.search(title)
+			if not title_match:
+				continue
+
+			ep_match = re_episode.search(title)
+			if not ep_match:
+				continue
+
+			title_idx = int(title_match.lastgroup[3:])
+			video = setting.settings['video'][title_idx]
+			ep = int(ep_match.group(1))
+
+			if ep <= video['ignore_ep_under']:
+				Logger.log('    {}({}) is ignored (previous episode than ep{})'.format(video['title'], ep, video['ignore_ep_under']))
+				continue
+			elif ep in setting.downloaded[video['title']]:
+				Logger.log('    {}({}) is ignored (already downloaded)'.format(video['title'], ep))
+				continue
+
+			link = urllib.parse.urljoin(top_url, link)
+			links.append(PageLink(video['title'], ep, link))
+
+			Logger.log('   found content page : {}({}), {}'.format(video['title'], ep, link))
+
+		return links
+
+	def crawl_downlink(self, page_link, soup):
+
+		links = []
+		if '신고된 게시물' in soup.find(id='writeContents').text:
+			return links
+
+		for a in soup.find_all('a'):
+			if 'href' in a.attrs and 'javascript:file_download' in a['href']:
+				jscript = a['href']
+				start = len("javascript:file_download('")
+				end = jscript.index("','")
+				sub_url = jscript[start:end]
+				url = urllib.parse.urljoin(page_link.url, sub_url)
+
+				file_name = jscript[end+3:-3]
+				file_name = urllib.parse.unquote(file_name)
+
+				torrent = TorrentFile(page_link.title, page_link.episode, file_name, url)
+				links.append(torrent)
+				Logger.log('    found download link : {}({})'.format(file_name, url))
+
+		return links

Crawler/WorkerTorrentKim.py

@@ -0,0 +1,79 @@
+import requests
+import urllib
+import bs4
+import re
+import os
+
+from .Setting import Setting
+from .ProxyHandler import ProxyHandler
+from .Logger import Logger
+from .Util import Util
+from .DataType import PageLink, TorrentFile
+
+
+class WorkerTorrentKim:
+	def crawl_list(self, top_url, soup, re_title, re_episode, setting):
+
+		links = []
+		tables = soup.select('table.board_list')
+		trs = tables[0].select('tr')
+		for tr in trs[1:]:
+			tds = tr.select('td.subject')
+			title = tds[0].text.strip()
+			link = tds[0].select('a')[0].attrs['href']
+
+			title_match = re_title.search(title)
+			if not title_match:
+				continue
+
+			ep_match = re_episode.search(title)
+			if not ep_match:
+				continue
+
+			title_idx = int(title_match.lastgroup[3:])
+			video = setting.settings['video'][title_idx]
+			ep = int(ep_match.group(1))
+
+			if ep <= video['ignore_ep_under']:
+				Logger.log('    {}({}) is ignored (previous episode than ep{})'.format(video['title'], ep, video['ignore_ep_under']))
+				continue
+			elif ep in setting.downloaded[video['title']]:
+				Logger.log('    {}({}) is ignored (already downloaded)'.format(video['title'], ep))
+				continue
+
+			link = urllib.parse.urljoin(top_url, link)
+			links.append(PageLink(video['title'], ep, link))
+
+			Logger.log('   found content page : {}({}), {}'.format(video['title'], ep, link))
+
+		return links
+
+	def crawl_downlink(self, page_link):
+		Logger.log('searching content page : {}({}) : {}'.format(page_link.title, page_link.episode, page_link.url))
+
+		resp = self.request_get(page_link.url)
+		soup = bs4.BeautifulSoup(resp.content.decode('utf8'), 'lxml')
+
+		links = []
+		file_table = soup.select('table#file_table')
+		a_tags = file_table[0].select('a')
+		torrent_links = [a for a in a_tags if '.torrent' in a.text]
+		smi_links = [a for a in a_tags if '.smi' in a.text]
+
+		for link in torrent_links:
+			file_name = link.text.strip()
+			sub_url = link.attrs['href']
+			url = urllib.parse.urljoin(page_link.url, sub_url)
+			links.append(TorrentFile(page_link.title, page_link.episode, file_name, url))
+
+			Logger.log('    found download link : {}({})'.format(file_name, url))
+
+		for link in smi_links:
+			file_name = link.text.strip()
+			sub_url = link.attrs['href']
+			url = urllib.parse.urljoin(link.url, sub_url)
+			links.append(TorrentFile(page_link.title, page_link.episode, file_name, url))
+
+			Logger.log('    found download link : {}({})'.format(file_name, url))
+
+		return links

Main.py

@@ -1,5 +1,10 @@
 from Crawler.Crawler import Crawler
+from Crawler.Crawler import Sorter
 
 if __name__ == '__main__':
+	
+	file_sorter = Sorter()
+	file_sorter.move_files()
+
 	crawler = Crawler()
 	crawler.crawl()

requirements.txt

@@ -1,2 +1,3 @@
 requests
 bs4
+yaml