def fetch_list(self, cat_id, page = 1):
vids = {}
response = urllib2.urlopen(self.video_list_url % (cat_id, page))
contents = response.read()
page = BeautifulSoup(contents)
matches = page.findAll('td', 'listOff')
if matches:
for match in matches:
primary_link = match.find('a', 'vodlink')
id = primary_link['href'].replace('./', '')
if id.startswith('javascript'):
continue
re_match = re.search(r'Posted: (\d+) (\d+)/(\d+)<', match.parent.find('td', 'sect').renderContents())
year = re_match.group(1)
month = re_match.group(2)
day = re_match.group(3)
date_string = "%s-%s-%s" % (day, month, year)
posted_date = datetime.date(int(year), int(month), int(day)).strftime(self.date_format)
image_url = 'http://www.gomtv.net' + match.find('img')['src']
local_image_path = os.path.join(self.base_data_path, cat_id, str(id) + '.tbn')
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))
if not os.path.isfile(local_image_path):
urllib.urlretrieve(image_url, local_image_path)
vids[id] = {'id': int(id),
'date_string': date_string,
'posted_date': posted_date,
'year': year,
'title': str(primary_link.string),
'description': str(match.find('div', 'vodinfo').renderContents()),
'image_url': local_image_path}
return vids
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
def fetch(self):
cats = {}
response = urllib2.urlopen(self.category_url)
contents = response.read()
page = BeautifulSoup(contents)
channels = page.findAll('div', {'id': 'Channels'})
if channels:
for channel in channels:
shows = channel.findAll('dl')
for show in shows:
if show.dt.a:
id = re.sub(r'/(.*)/', r'\1', show.dt.a['href'])
image_url = show.find('dd', 'img').img['src']
if image_url.startswith('/'):
image_url = 'http://www.gomtv.net' + image_url
if show.find('dd', 'txt'):
description = show.find('dd', 'txt').renderContents()
else:
description = ''
cats[id] = {'id': id, 'title': show.dt.a.string, 'description': description, 'image_url': image_url }
return cats
