def fetch_save_picture(url):
o = urlparse(url)
path = o.path
fpath = re.sub('^/', '', path)
fpath = re.sub('/', '-', fpath)
save_path = 'images/'+fpath
if os.path.exists(save_path):
print save_path, 'exists'
return
content = fetch.get_url(o.hostname, path)
# ff = open('get_url.cache', 'r')
# content = ff.read()
# ff.close()
f = open(save_path, 'w');
f.write(content);
f.close()
def get_save_page(page_num):
print page_num
url = '/7349086';
if page_num != 1:
url += '-'+str(page_num)
url += '.html'
content = fetch.get_url('bbs.hupu.com', url, {}, 'gbk')
scene_list = santi_parser.get_scene_list(content)
for scene in scene_list:
scene['text'] = scene['text'].strip()
m = re.match('(\d+)([a-z]?)', scene['number'])
scene['number'] = (m.group(1))
if m.group(2) is not None:
scene['number_extra'] = m.group(2)
db.insert('scene', scene)
print 'ok'
def get_info(uid):
content = fetch.get_url('www.renren.com', '/'+str(uid)+'/profile', {'v': 'info_timeline'})
info = parser.get_info(content)
return info
