def parse_next(next): dbpurl = DbpUrl(next) # fetch html src = fetch_html(dbpurl.get_url()) html = Html(src, dbpurl) # download photoes photoes = html.get_photoes() dl_photos(get_photo_list(photoes)) next = html.next_url() if next: parse_next(next)
def test(): albums = [ 'http://www.douban.com/photos/album/85642820/', # 7 'http://www.douban.com/online/10859460/album/51259013/', # 11 'http://site.douban.com/story/widget/photos/5857547/', # 4 'http://www.douban.com/photos/photo/1600191811/', # 3 'http://www.douban.com/online/11458796/photo/1852757882/', # 5 'http://site.douban.com/doubangongyi/widget/photos/11398597/photo/1775979493/' # 2 ] for url in albums: dbpurl = DbpUrl(url) if dbpurl.is_valid(): parse_html(dbpurl) else: print('unaccepted url')
def dbp_loop(): try: while True: url = raw_input(u2c('\n输入豆瓣相册地址: ')) dbpurl = DbpUrl(url) if dbpurl.is_valid(): parse_html(dbpurl) else: u2c_print('输入地址不合法TT') except (KeyboardInterrupt, SystemExit): # user wants to quit res = raw_input(u2c('\n确认退出程序?(Y/N)')) if res not in 'yY': dbp_loop() except Exception: u2c_print('\n出错误了TT!') dbp_loop()