Rename from socialmediascraper to snscrape

setup.py

@@ -2,14 +2,14 @@ import setuptools
 
 
 setuptools.setup(
-	name = 'socialmediascraper',
+	name = 'snscrape',
 	version = '0.0-dev',
-	description = 'A social media scraper',
-	packages = ['socialmediascraper'],
+	description = 'A social network service scraper',
+	packages = ['snscrape'],
 	install_requires = ['requests', 'lxml', 'beautifulsoup4'],
 	entry_points = {
 		'console_scripts': [
-			'smscrape = socialmediascraper.cli:main',
+			'snscrape = snscrape.cli:main',
 		],
 	},
 )

snscrape/cli.py

@@ -1,7 +1,7 @@
 import argparse
 import logging
-import socialmediascraper.base
-import socialmediascraper.modules
+import snscrape.base
+import snscrape.modules
 
 
 logger = logging.getLogger(__name__)
@@ -15,7 +15,7 @@ def parse_args():
 	parser.add_argument('-n', '--max-results', dest = 'maxResults', type = int, metavar = 'N', help = 'Only return the first N results')
 
 	subparsers = parser.add_subparsers(dest = 'scraper', help = 'The scraper you want to use')
-	classes = socialmediascraper.base.Scraper.__subclasses__()
+	classes = snscrape.base.Scraper.__subclasses__()
 	for cls in classes:
 		subparser = subparsers.add_parser(cls.name, formatter_class = argparse.ArgumentDefaultsHelpFormatter)
 		cls.setup_parser(subparser)

snscrape/modules/__init__.py

@@ -1,6 +1,6 @@
 import importlib
 import os
-import socialmediascraper.base
+import snscrape.base
 
 
 def _import_modules():
@@ -8,7 +8,7 @@ def _import_modules():
 	for fn in files:
 		if fn.endswith('.py') and fn != '__init__.py':
 			# Import module if not already imported
-			moduleName = f'socialmediascraper.modules.{fn[:-3]}'
+			moduleName = f'snscrape.modules.{fn[:-3]}'
 			module = importlib.import_module(moduleName)
 
 

snscrape/modules/facebook.py

@@ -2,14 +2,14 @@ import bs4
 import json
 import logging
 import re
-import socialmediascraper.base
+import snscrape.base
 import urllib.parse
 
 
 logger = logging.getLogger(__name__)
 
 
-class FacebookUserScraper(socialmediascraper.base.Scraper):
+class FacebookUserScraper(snscrape.base.Scraper):
 	name = 'facebook-user'
 
 	def __init__(self, username, **kwargs):

snscrape/modules/googleplus.py

@@ -3,13 +3,13 @@ import itertools
 import json
 import logging
 import re
-import socialmediascraper.base
+import snscrape.base
 
 
 logger = logging.getLogger(__name__)
 
 
-class GooglePlusUserScraper(socialmediascraper.base.Scraper):
+class GooglePlusUserScraper(snscrape.base.Scraper):
 	name = 'googleplus-user'
 
 	def __init__(self, user, **kwargs):
@@ -48,7 +48,7 @@ class GooglePlusUserScraper(socialmediascraper.base.Scraper):
 			logger.info('User has no posts')
 			return
 		for postObj in response[0][7]:
-			yield socialmediascraper.base.URLItem(f'https://plus.google.com/{postObj[6]["33558957"][21]}')
+			yield snscrape.base.URLItem(f'https://plus.google.com/{postObj[6]["33558957"][21]}')
 		cursor = response[0][1] # 'ADSJ_x'
 		if cursor is None:
 			# No further pages
@@ -86,7 +86,7 @@ class GooglePlusUserScraper(socialmediascraper.base.Scraper):
 			response = json.JSONDecoder().raw_decode(''.join(garbage[pos:]))[0] # Parses only the first structure in the data stream without throwing an error about the extra data at the end
 
 			for postObj in response[0][2]['74333095'][0][7]:
-				yield socialmediascraper.base.URLItem(f'https://plus.google.com/{postObj[6]["33558957"][21]}')
+				yield snscrape.base.URLItem(f'https://plus.google.com/{postObj[6]["33558957"][21]}')
 
 			cursor = response[0][2]['74333095'][0][1]
 

snscrape/modules/instagram.py

@@ -1,13 +1,13 @@
 import hashlib
 import json
 import logging
-import socialmediascraper.base
+import snscrape.base
 
 
 logger = logging.getLogger(__name__)
 
 
-class InstagramUserScraper(socialmediascraper.base.Scraper):
+class InstagramUserScraper(snscrape.base.Scraper):
 	name = 'instagram-user'
 
 	def __init__(self, username, **kwargs):
@@ -17,7 +17,7 @@ class InstagramUserScraper(socialmediascraper.base.Scraper):
 	def _response_to_items(self, response, username):
 		for node in response['user']['edge_owner_to_timeline_media']['edges']:
 			code = node['node']['shortcode']
-			yield socialmediascraper.base.URLItem(f'https://www.instagram.com/p/{code}/?taken-by={username}') #TODO: Do we want the taken-by parameter in here?
+			yield snscrape.base.URLItem(f'https://www.instagram.com/p/{code}/?taken-by={username}') #TODO: Do we want the taken-by parameter in here?
 
 	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'}

snscrape/modules/twitter.py

@@ -1,13 +1,13 @@
 import bs4
 import json
 import logging
-import socialmediascraper.base
+import snscrape.base
 
 
 logger = logging.getLogger(__name__)
 
 
-class TwitterSearchScraper(socialmediascraper.base.Scraper):
+class TwitterSearchScraper(snscrape.base.Scraper):
 	name = 'twitter-search'
 
 	def __init__(self, query, **kwargs):
@@ -23,7 +23,7 @@ class TwitterSearchScraper(socialmediascraper.base.Scraper):
 		for tweet in feed:
 			username = tweet.find('span', 'username').find('b').text
 			tweetID = tweet['data-item-id']
-			yield socialmediascraper.base.URLItem(f'https://twitter.com/{username}/status/{tweetID}')
+			yield snscrape.base.URLItem(f'https://twitter.com/{username}/status/{tweetID}')
 
 	def _check_json_callback(self, r):
 		if r.headers['content-type'] != 'application/json;charset=utf-8':