Refactor username vs ID mess

Closes #354

snscrape/modules/twitter.py

@@ -694,13 +694,13 @@ class TwitterSearchScraper(_TwitterAPIScraper):
 class TwitterUserScraper(TwitterSearchScraper):
 	name = 'twitter-user'
 
-	def __init__(self, username, isUserId = False, **kwargs):
-		if not self.is_valid_username(username):
+	def __init__(self, user, **kwargs):
+		self._isUserId = isinstance(user, int)
+		if not self._isUserId and not self.is_valid_username(user):
 			raise ValueError('Invalid username')
-		super().__init__(f'from:{username}', **kwargs)
-		self._username = username
-		self._isUserId = isUserId
-		self._baseUrl = f'https://twitter.com/{self._username}' if not self._isUserId else f'https://twitter.com/i/user/{self._username}'
+		super().__init__(f'from:{user}', **kwargs)
+		self._user = user
+		self._baseUrl = f'https://twitter.com/{self._user}' if not self._isUserId else f'https://twitter.com/i/user/{self._user}'
 
 	def _get_entity(self):
 		self._ensure_guest_token()
@@ -710,7 +710,7 @@ class TwitterUserScraper(TwitterSearchScraper):
 		else:
 			fieldName = 'userId'
 			endpoint = 'https://twitter.com/i/api/graphql/WN6Hck-Pwm-YP0uxVj1oMQ/UserByRestIdWithoutResults'
-		params = {'variables': json.dumps({fieldName: self._username, 'withHighlightedLabel': True}, separators = (',', ':'))}
+		params = {'variables': json.dumps({fieldName: str(self._user), 'withHighlightedLabel': True}, separators = (',', ':'))}
 		obj = self._get_api_data(endpoint, params = urllib.parse.urlencode(params, quote_via=urllib.parse.quote))
 		if not obj['data']:
 			return None
@@ -747,28 +747,28 @@ class TwitterUserScraper(TwitterSearchScraper):
 	def get_items(self):
 		if self._isUserId:
 			# Resolve user ID to username
-			self._username = self.entity.username
+			self._user = self.entity.username
 			self._isUserId = False
-			self._query = f'from:{self._username}'
+			self._query = f'from:{self._user}'
 		yield from super().get_items()
 
 	@staticmethod
 	def is_valid_username(s):
-		return (1 <= len(s) <= 15 and s.strip(string.ascii_letters + string.digits + '_') == '') or (s and s.strip(string.digits) == '')
+		return 1 <= len(s) <= 15 and s.strip(string.ascii_letters + string.digits + '_') == ''
 
 	@classmethod
 	def _cli_setup_parser(cls, subparser):
-		def username(s):
-			if cls.is_valid_username(s):
+		def user(s):
+			if cls.is_valid_username(s) or s.isdigit():
 				return s
-			raise ValueError('Invalid username')
+			raise ValueError('Invalid username or ID')
 
 		subparser.add_argument('--user-id', dest = 'isUserId', action = 'store_true', default = False, help = 'Use user ID instead of username')
-		subparser.add_argument('username', type = username, help = 'A Twitter username (without @)')
+		subparser.add_argument('user', type = user, help = 'A Twitter username (without @)')
 
 	@classmethod
 	def _cli_from_args(cls, args):
-		return cls._cli_construct(args, args.username, args.isUserId)
+		return cls._cli_construct(args, user = int(args.user) if args.isUserId else args.user)
 
 
 class TwitterProfileScraper(TwitterUserScraper):
@@ -778,7 +778,7 @@ class TwitterProfileScraper(TwitterUserScraper):
 		if not self._isUserId:
 			userId = self.entity.id
 		else:
-			userId = self._username
+			userId = self._user
 		paginationParams = {
 			'include_profile_interstitial_type': '1',
 			'include_blocking': '1',

snscrape/modules/weibo.py

@@ -52,24 +52,23 @@ class User(snscrape.base.Entity):
 class WeiboUserScraper(snscrape.base.Scraper):
 	name = 'weibo-user'
 
-	def __init__(self, name, uid, **kwargs):
+	def __init__(self, user, **kwargs):
 		super().__init__(**kwargs)
-		self._name = name
-		self._uid = uid
-		if self._name is None and self._uid is None:
-			raise ValueError('name or uid must not be None')
+		self._user = user
+		self._isUserId = isinstance(user, int)
 		self._headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.138 Safari/537.36'}
 
-	def _ensure_uid(self):
-		if self._uid is not None:
+	def _ensure_user_id(self):
+		if self._isUserId:
 			return
-		r = self._get(f'https://m.weibo.cn/n/{self._name}', headers = self._headers, allowRedirects = False)
+		r = self._get(f'https://m.weibo.cn/n/{self._user}', headers = self._headers, allowRedirects = False)
 		if r.status_code == 302 and r.headers['Location'].startswith('/u/') and len(r.headers['Location']) == 13 and r.headers['Location'][3:].strip('0123456789') == '':
 			# Redirect to uid URL
-			self._uid = int(r.headers['Location'][3:])
+			self._user = int(r.headers['Location'][3:])
+			self._isUserId = True
 		elif r.status_code == 200 and '<p class="h5-4con">用户不存在</p>' in r.text:
 			_logger.warning('User does not exist')
-			self._uid = _userDoesNotExist
+			self._user = _userDoesNotExist
 		else:
 			raise snscrape.base.ScraperError(f'Got unexpected response on resolving username ({r.status_code})')
 
@@ -99,13 +98,13 @@ class WeiboUserScraper(snscrape.base.Scraper):
 		  )
 
 	def get_items(self):
-		self._ensure_uid()
-		if self._uid is _userDoesNotExist:
+		self._ensure_user_id()
+		if self._user is _userDoesNotExist:
 			return
 		sinceId = None
 		while True:
 			sinceParam = f'&since_id={sinceId}' if sinceId is not None else ''
-			r = self._get(f'https://m.weibo.cn/api/container/getIndex?type=uid&value={self._uid}&containerid=107603{self._uid}&count=25{sinceParam}', headers = self._headers, responseOkCallback = self._check_timeline_response)
+			r = self._get(f'https://m.weibo.cn/api/container/getIndex?type=uid&value={self._user}&containerid=107603{self._user}&count=25{sinceParam}', headers = self._headers, responseOkCallback = self._check_timeline_response)
 			if r.status_code != 200:
 				raise snscrape.base.ScraperException(f'Got status code {r.status_code}')
 			o = r.json()
@@ -133,10 +132,10 @@ class WeiboUserScraper(snscrape.base.Scraper):
 		  )
 
 	def _get_entity(self):
-		self._ensure_uid()
-		if self._uid is _userDoesNotExist:
+		self._ensure_user_id()
+		if self._user is _userDoesNotExist:
 			return
-		r = self._get(f'https://m.weibo.cn/api/container/getIndex?type=uid&value={self._uid}', headers = self._headers)
+		r = self._get(f'https://m.weibo.cn/api/container/getIndex?type=uid&value={self._user}', headers = self._headers)
 		if r.status_code != 200:
 			raise snscrape.base.ScraperException('Could not fetch user info')
 		o = r.json()
@@ -144,14 +143,9 @@ class WeiboUserScraper(snscrape.base.Scraper):
 
 	@classmethod
 	def _cli_setup_parser(cls, subparser):
-		subparser.add_argument('user', type = snscrape.base.nonempty_string('user'), help = 'A user name or ID')
+		subparser.add_argument('--name', dest = 'isName', action = 'store_true', help = 'Use username instead of user ID')
+		subparser.add_argument('user', type = snscrape.base.nonempty_string('user'), help = 'A user ID')
 
 	@classmethod
 	def _cli_from_args(cls, args):
-		if len(args.user) == 10 and args.user.strip('0123456789') == '':
-			uid = args.user
-			name = None
-		else:
-			uid = None
-			name = args.user
-		return cls._cli_construct(args, name = name, uid = uid)
+		return cls._cli_construct(args, user = args.user if args.isName else int(args.user))