def sar_top_mp3(self):
from NXSpider.bin.models import artist_mo
if self.param_check(['artist'],
sys._getframe().f_code.co_name) is False:
return
download_type = self.parse_download()
artists = self.app.pargs.artist.split(',') # type: list
for arid in artists:
detail = api.get_artists_songs(arid)
if detail is None:
continue
artist_detail = detail['artist']
artist_detail['mp3'] = detail['hotSongs']
log.print_info(u"<{}>".format(artist_detail['name']))
artist_mo.parse_model(
artist_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 sab(self):
from NXSpider.bin.models import album_mo
if self.param_check(['album'],
sys._getframe().f_code.co_name) is False:
return
download_type = self.parse_download()
albums = self.app.pargs.album.split(',') # type: list
for pid in albums:
album_detail = api.get_album_detail(pid)
if album_detail is None:
continue
log.print_info(u"{} artist：{}".format(
"<" + album_detail['name'] + ">",
album_detail['artist']['name'],
))
album_mo.parse_model(
album_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 login_smv(self):
from NXSpider.bin.models import no_rec_mv_mo
if self.param_check(['lu'], sys._getframe().f_code.co_name) is False:
return
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()
mvs = api.my_mvs(session)
mvs = [api.get_mv_detail(d['id']) for d in mvs]
mvs = [d for d in mvs if d]
for mv in mvs:
no_rec_mv_mo.parse_model(
mv,
download_type=['mv'],
file_check=Config().get_file_check(),
shortcuts_stack=[] if Config().get_shortcut() else None)
log.print_info("spider complete!~")
pass
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 config_check(self):
self.config_show()
try:
config = Config()
if config.config_test():
log.print_info('config check complete, all is well done!')
except:
log.print_err('config check failed, pls re config')
def config_spider(self):
config = Config()
config_dict = config.config # type: dict
is_config = False
try:
if self.app.pargs.path_download is not None:
paths = self.app.pargs.path_download.split(',') # type: list
if default_path_key in paths:
index = paths.index(default_path_key)
paths.remove(default_path_key)
paths.insert(index, default_download_dir)
final_paths = []
for p in paths:
try:
# some error need pass
if os.path.isdir(p) is False:
os.mkdir(p)
final_paths.append(p)
except:
log.print_warn("path may be wrong and be deleted: {}".format(p))
pass
if not final_paths:
final_paths.append(default_download_dir)
log.print_info('path will be set as: ' + ','.join(final_paths))
config_dict['download_path'] = final_paths
is_config = True
if self.app.pargs.mv_resolution is not None:
r = int(self.app.pargs.mv_resolution)
if r not in mv_resolutions:
log.print_warn("-mvr resolution config skip, value must be 240,480,720,1080")
config_dict['mv_def_resolution'] = r
is_config = True
if self.app.pargs.media_tag is not None:
config_dict['media_tag'] = True if self.app.pargs.media_tag.lower() == 'true'\
or self.app.pargs.media_tag == '1' else False
is_config = True
if self.app.pargs.media_tag_163 is not None:
config_dict['media_tag_163'] = True if self.app.pargs.media_tag_163.lower() == 'true' \
or self.app.pargs.media_tag_163 == '1' else False
is_config = True
except:
log.print_err("input error, pls check")
raise
if is_config:
config.save_config_file()
log.print_info("config success")
self.config_show()
def download_file(self, doc):
"""
download file from music 163
:param doc:
:return:
"""
file_relative_path = self.download_relative_path(doc)
path = Config().get_path()
content = self.request_file(doc)
if content is None:
log.print_err(u"file download failed : %s" % file_relative_path)
return False
try:
file_name = os.path.join(path, file_relative_path)
# dir make
dir_name = os.path.dirname(file_name)
if not os.path.exists(dir_name):
os.makedirs(dir_name)
# file write
with open(file_name, "wb") as code:
code.write(content)
self.download_file_tag(file_name, doc)
log.print_info(u"file download complete: %s" % file_relative_path)
self.download_log(doc)
return True
except Exception as e:
log.print_err("file save failed : %s, err: %s" %
(file_relative_path, e))
return False
def attach_mp4_tag(doc, file):
"""
:type doc: Mp4Model
:param doc:
:param file:
:return:
"""
authors = u",".join([x['name'] for x in doc.artists])
data = {
'title': doc['name'],
'artist': authors,
}
if Config().get_media_tag_163():
comment_plaintext = u'mv:{"title":"%s","mvId":%d,"artistId":%d,' \
u'"artistName":"%s","pubTime":"%s","bitrate":%d}' \
% (doc['name'], doc.id, doc.artists[0].id,
doc.artists[0]['name'], doc['publishTime'],
doc['download_video_r'])
comment = "163 key(Don't modify):" + aes_ecb(comment_plaintext, aes_code).decode()
data['comment'] = comment
try:
mp4 = MP4(file)
for k, v in data.items():
if k not in mugagen_mp4_key_map:
continue
mp4[mugagen_mp4_key_map[k]] = v
mp4.save()
except Exception as e:
return False
return True
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 create_shortcut(self, doc, shortcuts_stack):
"""
:param doc:
:param shortcuts_stack:
:type shortcuts_stack: list[str]
:return:
"""
from NXSpider.utility.shortcut import symlink
if not (hasattr(doc, model_is_download) and doc[model_is_download]
and hasattr(doc, model_download_path) and os.path.exists(
doc[model_download_path]) and self.download_filename(doc)):
return
file_path = doc[model_download_path]
shortcut_root = os.path.join(Config().get_path(), 'shortcuts')
file_name = self.download_filename(doc)
if file_path and file_path is not True:
if shortcuts_stack:
path = os.path.join(shortcut_root, *shortcuts_stack)
os.makedirs(path, exist_ok=True)
target = os.path.join(path, file_name)
symlink(file_path, os.path.join(shortcut_root, target))
for k in self.shortcut_self_path(doc):
path = os.path.join(shortcut_root, k)
os.makedirs(path, exist_ok=True)
target = os.path.join(path, file_name)
symlink(file_path, os.path.join(shortcut_root, target))
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 stop_mvs(self):
from NXSpider.bin.models import no_rec_mv_mo
mvs = api.top_mvs(offset=self.app.pargs.offset or 0,
limit=self.app.pargs.limit or 50)
mvs = [api.get_mv_detail(d['id']) for d in mvs]
mvs = [d for d in mvs if d]
for mv in mvs:
no_rec_mv_mo.parse_model(
mv,
download_type=['mv'],
file_check=Config().get_file_check(),
shortcuts_stack=[] if Config().get_shortcut() else None)
log.print_info("spider complete!~")
pass
def debug_save_json(self, obj):
with tools.ignored(Exception):
relative_path = os.path.join(
self.__file_type__ + '.debug',
self.__file_type__ + "_" + str(obj['id']) + '.json')
file_name = os.path.join(Config().get_path(), relative_path)
with codecs.open(file_name, "wb", encoding='utf8') as code:
test = json.dumps(obj, ensure_ascii=False)
code.write(test)
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 smp3s(self):
from NXSpider.bin.models import dw_mp3_mo
if self.param_check(['mp3'], sys._getframe().f_code.co_name) is False:
return
download_type = self.parse_download()
mp3s = self.app.pargs.mp3.split(',') # type: list
details = api.get_mp3_details(mp3s)
for mid, detail in details.items():
log.print_info(u"<{}>".format(detail['name']))
dw_mp3_mo.parse_model(
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 url_load(self, doc):
"""
implement pls
:param doc:
:return:
:rtype: str
"""
try:
target_r = get_target_r(doc, Config().get_mv_resolution())
doc['download_video_r'] = target_r
return get_video_link(doc['id'], target_r)
except:
return None
def config_mongo(self):
config = Config()
config_dict = config.config # type: dict
mongo_key = 'mongo'
is_config = False
try:
if self.app.pargs.mhost is not None:
config_dict[mongo_key]['host'] = self.app.pargs.mhost
config_dict['no_mongo'] = False
is_config = True
if self.app.pargs.mport is not None:
config_dict[mongo_key]['port'] = int(self.app.pargs.mport)
is_config = True
if self.app.pargs.muser is not None:
config_dict[mongo_key]['username'] = self.app.pargs.muser
is_config = True
if self.app.pargs.mpassword is not None:
config_dict[mongo_key]['password'] = self.app.pargs.mpassword
is_config = True
if self.app.pargs.mdbname is not None:
config_dict[mongo_key]['name'] = self.app.pargs.mdbname
is_config = True
if self.app.pargs.nomongo is not None:
config_dict['no_mongo'] = True if self.app.pargs.nomongo.lower() == 'true'\
or self.app.pargs.nomongo == '1' else False
is_config = True
except:
log.print_err("input error, pls check")
raise
if is_config:
config.save_config_file()
log.print_info("config success")
self.config_show()
def sar_albums(self):
from NXSpider.bin.models import artist_album_mo
if self.param_check(['artist'],
sys._getframe().f_code.co_name) is False:
return
download_type = self.parse_download()
artists = self.app.pargs.artist.split(',') # type: list
for arid in artists:
detail = api.get_artist_album(arid,
offset=self.app.pargs.offset or 0,
limit=self.app.pargs.limit or 50)
if detail is None:
continue
artist_detail = detail['artist']
album_details = [
api.get_album_detail(d['id']) for d in detail['hotAlbums']
]
album_details = [d for d in album_details if d]
artist_detail['albums'] = album_details
log.print_info(u"<{}>".format(artist_detail['name']))
log.print_info("albums bellow will be crawled")
print_albums(artist_detail['albums'])
artist_album_mo.parse_model(
artist_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 attach_mp3_idv3(doc, file):
"""
:type doc: Mp3Model
:param doc:
:param file:
:return:
"""
artists = [('["%s",%d]' % (x['name'], x.id)) for x in doc.artists]
artists_str = reduce(lambda x, y: x + "," + y, artists)
authors = reduce(lambda x, y: x + ',' + y,
[x['name'] for x in doc.artists])
data = {
'title': doc['name'],
'artist': authors,
'album': doc['album']['name'],
'album_artist': authors,
'track_num': str(doc['no']),
}
if Config().get_media_tag_163():
comment_plaintext = u'music:{"musicId":%d,"musicName":"%s","bitrate":320000,' \
u'"albumId":%d,"album":"%s", "artist":[%s]}' \
% (doc.id, doc['name'], doc.album.id, doc.album['name'],
artists_str)
comment = "163 key(Don't modify):" + aes_ecb(comment_plaintext,
aes_code).decode()
data['comment'] = comment
try:
mp3 = ID3(file, v2_version=3)
for k, v in data.items():
if k not in mutagen_idv3_key_map:
continue
if k == 'comment':
mp3.add(id3.COMM(lang='XXX', text=v))
continue
attr_type = getattr(id3, mutagen_idv3_key_map[k], None)
if attr_type:
mp3.add(attr_type(text=v))
mp3.save(v2_version=3)
except Exception as e:
return False
return True
def download_check(self, doc, check_file=False):
"""
:param doc:
:param check_file: check dist file to download
:type doc: DynamicDocument
:return:
"""
if check_file:
file_relative_path = self.download_relative_path(doc)
for path in Config().get_paths():
file_path = os.path.join(path, file_relative_path)
if os.path.exists(file_path):
self.download_log(doc, download_path=file_path)
return file_path
self.download_log(doc, downloaded=False)
return False
return hasattr(doc, model_is_download) and doc[model_is_download]
def sar_albums(self):
from NXSpider.bin.models import artist_album_mo
if self.param_check(['artist'],
sys._getframe().f_code.co_name) is False:
return
download_type = self.parse_download()
artists = self.app.pargs.artist.split(',') # type: list
for arid in artists:
detail = api.get_artist_album(arid,
offset=self.app.pargs.offset or 0,
limit=self.app.pargs.limit or 50)
if detail is None:
continue
artist_detail = detail['artist']
album_details = [
api.get_album_detail(d['id']) for d in detail['hotAlbums']
]
album_details = [d for d in album_details if d]
artist_detail['albums'] = album_details
from terminaltables import AsciiTable
table = AsciiTable([["ID", "Album", "Artist", "ArtistID"]])
table_data = [[
str(item['id']),
item['name'],
','.join([ar['name'] for ar in item['artists']]),
','.join([str(ar['id']) for ar in item['artists']]),
] for item in artist_detail['albums']]
table.table_data.extend(table_data)
log.print_info(u"<{}>".format(artist_detail['name']))
log.print_info("albums bellow will be crawled")
print(table.table)
artist_album_mo.parse_model(artist_detail,
download_type=download_type,
file_check=Config().get_file_check())
log.print_info("spider complete!~")
pass
def get_target_r(obj, limit_r=Config().get_mv_resolution()):
max_valid = max([x['resolution'] for x in obj['resolutions']])
return limit_r if max_valid > limit_r else max_valid
def download_file_tag(self, filename, doc):
if self.__file_type__ in ['mp3', 'mp4', 'mv'] \
and Config().get_media_tag():
attach_media_tag(doc, filename)
def config_clear(self):
Config().config_reset()
log.print_info("config has been reset, u need re-config from beginning pls")
self.config_show()
#!/usr/bin/env python # -*- coding: utf-8 -*- # # created by Lipson on 2018/6/20. # email to [email protected] # from NXSpider.common.config import Config if Config().get_no_mongo(): from NXSpider.model.dict_model import * else: from NXSpider.model.mongo_model import * model_download_url = 'download_url' model_is_download = 'downloaded' model_download_path = 'download_path' __all__ = [ 'ConfigModel', 'UserModel', 'AlbumModel', 'PlaylistModel', 'Mp4Model', 'VideoModel', 'ArtistModel', 'Mp3Model', 'AuthorModel', 'update_dynamic_doc', 'model_download_url', 'model_is_download', 'get_one_model_by_key',
import os
import shutil
from NXSpider.common.config import Config
from NXSpider.model.mongo_model import Mp3Model, Mp4Model
from NXSpider.spider.mp3 import Mp3
from NXSpider.spider.mv import MV
from NXSpider.common import tools, log, constant
from NXSpider.spider.base_driver import Music163Obj
from NXSpider.utility.media_tag import attach_media_tag
media_types = {
'mp3': [Mp3Model, Mp3],
'mp4': [Mp4Model, MV],
}
paths = Config().get_paths()
def attach_media_idv3_by_db():
"""
attach media idv3 by paths in config
:return:
"""
for suffix, type_setting in media_types:
model, driver = type_setting # type: Mp3Model or Mp4Model, Music163Obj
objs = model.objects(downloaded=True)
for obj in objs:
file_path = driver.download_check(obj, check_file=True)
if not file_path:
continue
# # created by Lipson on 2018/4/19. # email to [email protected] # from datetime import datetime import pymongo from mongoengine import connect, DynamicDocument, Document, signals from mongoengine.fields import * from pymongo.errors import ServerSelectionTimeoutError from NXSpider.common import log from NXSpider.common.config import Config from NXSpider.model.export import * mongodb_conf = Config().get_mongo() try: client = pymongo.MongoClient(host=mongodb_conf['host'], port=mongodb_conf['port'], connectTimeoutMS=3000, serverSelectionTimeoutMS=3000) test_connect = client.database.test.count() del client except ServerSelectionTimeoutError as e: log.print_err("mongodb server config error") exit() model_download_url = 'download_url' model_is_download = 'downloaded'
def config_show(self):
config_dict = Config().config
log.print_info("config will be show fellow:")
print(json.dumps(config_dict, ensure_ascii=False, indent=1))