def fetch_page_count(self, cat_id):
count = 0
response = urllib2.urlopen(self.video_list_url % (cat_id, 1))
contents = response.read()
page = BeautifulSoup(contents)
link_table = page.find('table', {'id': 'bbsnum'})
count = re.search(r"<a href=\"\./\?page=(\d+)&[^>]*>Last >></a>", link_table.renderContents()).group(1)
return count
def fetch_video(self, cat_id, vid_id):
vid = None
response = urllib2.urlopen(self.video_url % (cat_id, vid_id))
contents = response.read()
page = BeautifulSoup(contents)
re_match = re.search(r'\.swf\?link=(\d+)', page.renderContents())
if re_match:
vid = {}
file_id = re_match.group(1)
vid['title'] = page.find('div', {'id': 'bbsDetail'}).h3.string
vid['file_url'] = 'http://flvdn.gomtv.net/viewer/%s.flv' % file_id
if not os.path.exists(os.path.join(self.base_data_path, cat_id)):
os.makedirs(os.path.join(self.base_data_path, cat_id))
vid['local_vid_path'] = os.path.join(self.base_data_path, cat_id, str(vid_id) + '.flv')
return vid
