def spls(self):
from NXSpider.bin.models import playlist_mo
if self.param_check(['playlist'],
sys._getframe().f_code.co_name) is False:
return
download_type = self.parse_download()
playlists = self.app.pargs.playlist.split(',') # type: list
for pid in playlists:
playlist_detail = api.get_playlist_detail(pid)
if playlist_detail:
log.print_info(u"<{}> author：{}".format(
playlist_detail['name'],
playlist_detail['creator']['nickname'],
))
playlist_mo.parse_model(
playlist_detail,
download_type=download_type,
file_check=Config().get_file_check(),
shortcuts_stack=[] if Config().get_shortcut() else None)
log.print_info("spider complete!~")
pass
def sur_pls(self):
from NXSpider.bin.models import playlist_mo
if self.param_check(['user'], sys._getframe().f_code.co_name) is False:
return
download_type = self.parse_download()
user_id = self.app.pargs.user
playlists = api.user_playlist(user_id,
offset=self.app.pargs.offset or 0,
limit=self.app.pargs.limit or 50)
log.print_info("playlists bellow will be crawled")
print_playlist(playlists)
for pl_obj in playlists:
playlist_detail = api.get_playlist_detail(pl_obj['id'])
if playlist_detail:
log.print_info(u"<{}> author：{}".format(
playlist_detail['name'],
playlist_detail['creator']['nickname'],
))
playlist_mo.parse_model(
playlist_detail,
download_type=download_type,
file_check=Config().get_file_check(),
shortcuts_stack=[] if Config().get_shortcut() else None)
log.print_info("spider complete!~")
pass
def scls_pls(self):
from NXSpider.bin.models import playlist_mo
if self.param_check(['cls'], sys._getframe().f_code.co_name) is False:
return
download_type = self.parse_download()
class_name = self.app.pargs.cls
class_name = py2_decoding(class_name)
if class_name != u"全部" and py2_encoding(
class_name) not in api.ALL_CLASSES:
log.print_err(
"class name is wrong, pls check by run : nxspider sw-pl-classes"
)
return
playlists = api.get_top_playlists(category=class_name,
offset=self.app.pargs.offset or 0,
limit=self.app.pargs.limit
or 50) # type: list
for pl_obj in playlists:
playlist_detail = api.get_playlist_detail(pl_obj['id'])
if playlist_detail:
log.print_info(u"<{}> author：{}".format(
playlist_detail['name'],
playlist_detail['creator']['nickname'],
))
playlist_mo.parse_model(playlist_detail,
download_type=download_type,
file_check=Config().get_file_check())
log.print_info("spider complete!~")
pass
def sur_pls(self):
from NXSpider.bin.models import playlist_mo
if self.param_check(['user'], sys._getframe().f_code.co_name) is False:
return
download_type = self.parse_download()
user_id = self.app.pargs.user
playlists = api.user_playlist(user_id)
from terminaltables import AsciiTable
table = AsciiTable([["ID", "Name", "User", "PlayCount"]])
table_data = [[
str(item['id']),
item['name'],
item['creator']['nickname'],
str(item['playCount']),
] for item in playlists]
table.table_data.extend(table_data)
log.print_info("playlists bellow will be crawled")
print(table.table)
for pl_obj in playlists:
playlist_detail = api.get_playlist_detail(pl_obj['id'])
if playlist_detail:
log.print_info(u"<{}> author：{}".format(
playlist_detail['name'],
playlist_detail['creator']['nickname'],
))
playlist_mo.parse_model(playlist_detail,
download_type=download_type,
file_check=Config().get_file_check())
log.print_info("spider complete!~")
pass
def playlist_by_id(link,
download_type=all_download_type,
save=True,
file_check=True):
playlist_detail = get_playlist_detail(link)
with tools.ignored(Exception):
log.print_info("%s author：%s" % (
"<" + playlist_detail['name'] + ">",
playlist_detail['creator']['nickname'],
))
playlist_mo = Playlist()
playlist_mo.parse_model(playlist_detail,
save=save,
download_type=download_type,
file_check=file_check)
pass
def login_spls(self):
if self.param_check(['lu', 'lp'],
sys._getframe().f_code.co_name) is False:
return
from NXSpider.bin.models import playlist_mo
plaintext_pwd = self.app.pargs.lp or None
if plaintext_pwd is None:
import getpass
plaintext_pwd = getpass.getpass("Please input your password:"******"none")))
exit()
user_id = res['account']['id']
download_type = self.parse_download()
playlists = api.user_playlist(user_id,
offset=self.app.pargs.offset or 0,
limit=self.app.pargs.limit or 1000)
log.print_info("playlists bellow will be crawled")
print_playlist(playlists)
for pl_obj in playlists:
playlist_detail = api.get_playlist_detail(pl_obj['id'])
if playlist_detail:
log.print_info(u"<{}> author：{}".format(
playlist_detail['name'],
playlist_detail['creator']['nickname'],
))
playlist_mo.parse_model(
playlist_detail,
download_type=download_type,
file_check=Config().get_file_check(),
shortcuts_stack=[] if Config().get_shortcut() else None)
log.print_info("spider complete!~")
pass
def crawl_playlist_by_page(page,
dtype="全部",
download_type=['mp3', 'mv'],
save=True,
file_check=True):
play_url = "http://music.163.com/discover/playlist/?order=hot&cat={}&limit=35&offset={}"
play_url = play_url.format(dtype, page * 35)
playlist_id = []
titles = []
try:
acmsk = {'class': 'msk'}
scnb = {'class': 'nb'}
dcu = {'class': 'u-cover u-cover-1'}
ucm = {'class': 'm-cvrlst f-cb'}
data = tools.curl(play_url, headers, type=RETURE_HTML)
lst = data.find('ul', ucm)
for play in lst.find_all('div', dcu):
title = play.find('a', acmsk)['title']
link = play.find('a', acmsk)['href'].replace("/playlist?id=", "")
playlist_detail = get_playlist_detail(link)
with tools.ignored(Exception):
log.print_info("%s author：%s" % (
"<" + playlist_detail['name'] + ">",
tools.encode(playlist_detail['creator']['nickname']),
))
playlist_mo = Playlist()
playlist_mo.parse_model(playlist_detail,
save=save,
download_type=download_type,
file_check=file_check)
return titles
except Exception as e:
log.print_err("crawl html error：{} type：{} page：{}".format(
e, dtype, page))
raise
# except Exception as e:
# log.print_err("playlist page error：{} type：{} page：{}".format(e, type, page))
# log.print_err(e)
# def playlist_all_page():
# cf = "全部"
# for i in range(36):
# playlist_by_page(i + 1, cf)
# test = get_mv_details([5322493,239037])
test = get_classify()
test = get_playlist_catelogs()
test = get_playlist_classes()
test = get_top_playlists()
test = user_playlist(48872048)
test = get_playlist_detail(92024088)
test = get_playlist_detail(2246057871)
test = get_playlist_detail(107020750)
test = get_playlist_detail_v3(107020750)
p = hashlib.md5('000'.encode('utf-8')).hexdigest()
s = requests.Session()
test = login('15302663382', p, s)
test = user_playlist(92024088, session=s)
test = get_playlist_detail(107020750)
test = search('周杰伦', stype=100)
test = top_artists()
test = get_playlist_classes()
test = get_mp3_details([412902496, 412902496, 412902496])