Version 0.1.3

setup.py

@@ -3,7 +3,7 @@ import setuptools
 
 setuptools.setup(
 	name = 'snscrape',
-	version = '0.1.2',
+	version = '0.1.3',
 	description = 'A social networking service scraper',
 	author = 'JustAnotherArchivist',
 	url = 'https://github.com/JustAnotherArchivist/snscrape',

snscrape/base.py

@@ -59,11 +59,32 @@ class Scraper:
 				logger.debug(f'... with data: {data!r}')
 			try:
 				r = self._session.send(req, timeout = timeout)
-				if responseOkCallback is None or responseOkCallback(r):
-					logger.debug(f'{req.url} retrieved successfully')
-					return r
 			except requests.exceptions.RequestException as exc:
-				logger.error(f'Error retrieving {url}: {exc!r}')
+				if attempt < self._retries:
+					retrying = ', retrying'
+					level = logging.WARNING
+				else:
+					retrying = ''
+					level = logging.ERROR
+				logger.log(level, f'Error retrieving {req.url}: {exc!r}{retrying}')
+			else:
+				if responseOkCallback is not None:
+					success, msg = responseOkCallback(r)
+				else:
+					success, msg = (True, None)
+				msg = f': {msg}' if msg else ''
+
+				if success:
+					logger.debug(f'{req.url} retrieved successfully{msg}')
+					return r
+				else:
+					if attempt < self._retries:
+						retrying = ', retrying'
+						level = logging.WARNING
+					else:
+						retrying = ''
+						level = logging.ERROR
+					logger.log(level, f'Error retrieving {req.url}{msg}{retrying}')
 			if attempt < self._retries:
 				sleepTime = 1.0 * 2**attempt # exponential backoff: sleep 1 second after first attempt, 2 after second, 4 after third, etc.
 				logger.info(f'Waiting {sleepTime:.0f} seconds')

snscrape/modules/twitter.py

@@ -27,16 +27,15 @@ class TwitterSearchScraper(snscrape.base.Scraper):
 
 	def _check_json_callback(self, r):
 		if r.headers['content-type'] != 'application/json;charset=utf-8':
-			logger.error(f'Content type of {r.url} is not JSON')
-			return False
-		return True
+			return False, f'content type is not JSON'
+		return True, None
 
 	def get_items(self):
 		headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36'}
 
 		# First page
 		logger.info(f'Retrieving search page for {self._query}')
-		r = self._get('https://twitter.com/search', params = {'f': 'tweets', 'vertical': 'default', 'lang': 'en', 'q': self._query, 'src': 'typd'}, headers = headers)
+		r = self._get('https://twitter.com/search', params = {'f': 'tweets', 'vertical': 'default', 'lang': 'en', 'q': self._query, 'src': 'typd', 'qf': 'off'}, headers = headers)
 
 		feed = self._get_feed_from_html(r.text)
 		if not feed:
@@ -57,6 +56,7 @@ class TwitterSearchScraper(snscrape.base.Scraper):
 					'include_entities': '1',
 					'reset_error_state': 'false',
 					'src': 'typd',
+					'qf': 'off',
 					'max_position': maxPosition,
 				},
 				headers = headers,