def get_keyworld(keyworld_pages): for keyworld_page in keyworld_pages: headers = { 'User-Agent': 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)', 'Referer': 'http://www.zhihu.com/articles' } try: request = urllib2.Request( url="http://www.torrentkitty.org{link}".format( link=keyworld_page.get("href")), headers=headers) response = urllib2.urlopen(request) content = response.read() except: pass else: if content: soup = BeautifulSoup(content) results = soup.find_all(href=re.compile("/search/")) for result in results: print result link = result.get('href') title = result.get('title') bfs = BF_ROOT.add(link) if bfs is False and title is not None: Rootport.objects.create( title=title, link="http://www.torrentkitty.org{link}".format( link=link))
def get_root_port(): headers = {'User-Agent': 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)', 'Referer': 'http://www.zhihu.com/articles'} request = urllib2.Request( url="http://www.torrentkitty.org/search/", headers=headers) response = urllib2.urlopen(request) content = response.read() if content: soup = BeautifulSoup(content) results = soup.find_all(href=re.compile("/search/")) for result in results: link = result.get('href') title = result.string bfs = BF_ROOT.add(link) if bfs is False: Rootport.objects.create( title=title, link="http://www.torrentkitty.org{link}".format(link=link))
def get_root_port(): headers = { 'User-Agent': 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)', 'Referer': 'http://www.zhihu.com/articles' } request = urllib2.Request(url="http://www.torrentkitty.org/search/", headers=headers) response = urllib2.urlopen(request) content = response.read() if content: soup = BeautifulSoup(content) results = soup.find_all(href=re.compile("/search/")) for result in results: link = result.get('href') title = result.string bfs = BF_ROOT.add(link) if bfs is False: Rootport.objects.create( title=title, link="http://www.torrentkitty.org{link}".format(link=link))
def get_keyworld(keyworld_pages): for keyworld_page in keyworld_pages: headers = {'User-Agent': 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)', 'Referer': 'http://www.zhihu.com/articles'} try: request = urllib2.Request(url="http://www.torrentkitty.org{link}".format(link=keyworld_page.get("href")), headers=headers) response = urllib2.urlopen(request) content = response.read() except: pass else: if content: soup = BeautifulSoup(content) results = soup.find_all(href=re.compile("/search/")) for result in results: print result link = result.get('href') title = result.get('title') bfs = BF_ROOT.add(link) if bfs is False and title is not None: Rootport.objects.create( title=title, link="http://www.torrentkitty.org{link}".format(link=link))