class TestNewTableCreation:
""" Make sure you can create new tables after recieving new table
names. """
def __init__(self):
self.cls_initialized = False
def setUp(self):
assert not self.cls_initialized
self.cls_initialized = True
#self.path = os.path.abspath("") + "/GatherNews/gathernews/tests/"
self.path = os.path.abspath("") + "/gathernews/tests/"
self.capture_feeds = CaptureFeeds(self.path)
def tearDown(self):
assert self.cls_initialized
self.cls_initialized = False
def test_make_table_names(self):
""" Parse an RSS link and create a table name """
# Set parameters
RSS_link = "http://feeds.reuters.com/Reuters/worldNews"
create_these_tables = []
# Run test
assert_true(self.capture_feeds.make_table_names(RSS_link,
create_these_tables)\
[0] == "ReutersWorldNews")
def test_match_names(self):
""" Make sure a SQL database table name can be matched to a table
name used in an insert query. """
# Set parameters
query_name = "ReutersWorldNews"
# Run test
assert_true(self.capture_feeds.match_names(query_name) == True)
# Note that this method is actually part of the
# PopulateExistingTables() test class. However, the file path
# used for testing is shared with the TestNewTablesCreated2()
# class so here we've arrived.
def test_do_tables_exist(self):
""" See if tables which should be created are not found when they
do not exist
The error should be raised here from read_file()
"""
tables = self.capture_feeds.do_tables_exist
assert_false(tables())
def test_create_these_tables(self):
""" Make sure an error is raised if no RSS links have been added to
'feeds_list.txt' """
# Set parameters
current_feeds_list = []
previous_feeds_list = [] # empty list should never be returned here
# Run test
assert_raises(UserWarning, self.capture_feeds.create_these_tables,
current_feeds_list, previous_feeds_list)
def do_everything2(path):
""" load_db() in 0.2.0 achieves the same thing as the benchmark function
populate_and_rm_dups() seen above """
start = time.time()
capture_feeds = CaptureFeeds(path)
capture_feeds.load_db()
total = time.time() - start
print "Elapsed time: ", total
return total
def do_everything(path):
start = time.time()
capture_feeds = CaptureFeeds(path)
capture_feeds.create_tables()
capture_feeds.populate_db()
capture_feeds.rm_duplicates()
total = time.time() - start
print "Elapsed time: ", total
return total # database must be removed each time
class BenchmarkgRSS:
def __init__(self):
# File path to where "feeds_list.txt" is located
file_path = "/home/tyler/code/GatherNews/gathernews/tests/"
self.capture_feeds = CaptureFeeds(file_path)
def benchmark_create_tables(self):
""" Test create_tables() method as well as supporting methods
get_RSS_link()
get_tablenames()
# do_tables_exist() -- this is not working
"""
start = time.time()
self.capture_feeds.load_db()
total = time.time() - start
print "Elapsed time: ", total
return total
def populate_and_rm_dups(path):
start = time.time()
capture_feeds = CaptureFeeds(path)
capture_feeds.populate_db()
capture_feeds.rm_duplicates()
total = time.time() - start
print "Elapsed time: ", total
return total
def setUp(self):
assert not self.cls_initialized
self.cls_initialized = True
self.path = os.path.abspath("") + "/GatherNews/gathernews/tests/"
self.capture_feeds = CaptureFeeds(self.path)
self.rm_garbage = FilterGarbage()
""" ======================================== Loading multiple RSS feeds into SQLite3 ======================================== An example showing how GatherNews can be used load news articles from RSS feeds into a database. This example allows you to create new tables and load a SQLite3 database with News from multiple RSS feeds. Feel free to contact me if you run into any problems. """ print(__doc__) # Author: Tyler Brown <*****@*****.**> # Import RSS feed capture class from gathernews.gRSS import CaptureFeeds # File path to where "feeds_list.txt" is located file_path = "/home/tyler/code/GatherNews/examples/" # Instantiate the class capture_feeds = CaptureFeeds(file_path) # Create tables, load database, remove duplicates capture_feeds.load_db()
def setUp(self):
assert not self.cls_initialized
self.cls_initialized = True
#self.path = os.path.abspath("") + "/GatherNews/gathernews/tests/"
self.path = os.path.abspath("") + "/gathernews/tests/"
self.capture_feeds = CaptureFeeds(self.path)
def __init__(self):
# File path to where "feeds_list.txt" is located
file_path = "/home/tyler/code/GatherNews/gathernews/tests/"
self.capture_feeds = CaptureFeeds(file_path)
class TestNewTableCreation:
""" Make sure you can create new tables after recieving new table
names. """
def __init__(self):
self.cls_initialized = False
def setUp(self):
assert not self.cls_initialized
self.cls_initialized = True
#self.path = os.path.abspath("") + "/GatherNews/gathernews/tests/"
self.path = os.path.abspath("") + "/gathernews/tests/"
self.capture_feeds = CaptureFeeds(self.path)
def tearDown(self):
assert self.cls_initialized
self.cls_initialized = False
def test_make_table_names(self):
""" Parse an RSS link and create a table name """
# Set parameters
RSS_link = "http://feeds.reuters.com/Reuters/worldNews"
create_these_tables = []
# Run test
assert_true(self.capture_feeds.make_table_names(RSS_link,
create_these_tables)\
[0] == "ReutersWorldNews")
def test_match_names(self):
""" Make sure a SQL database table name can be matched to a table
name used in an insert query. """
# Set parameters
query_name = "ReutersWorldNews"
# Run test
assert_true(self.capture_feeds.match_names(query_name) == True)
# Note that this method is actually part of the
# PopulateExistingTables() test class. However, the file path
# used for testing is shared with the TestNewTablesCreated2()
# class so here we've arrived.
def test_do_tables_exist(self):
""" See if tables which should be created are not found when they
do not exist
The error should be raised here from read_file()
"""
tables = self.capture_feeds.do_tables_exist
assert_false(tables())
def test_create_these_tables(self):
""" Make sure an error is raised if no RSS links have been added to
'feeds_list.txt' """
# Set parameters
current_feeds_list = []
previous_feeds_list = [] # empty list should never be returned here
# Run test
assert_raises(UserWarning, self.capture_feeds.create_these_tables,
current_feeds_list, previous_feeds_list)
def setUp(self):
assert not self.cls_initialized
self.cls_initialized = True
#self.path = os.path.abspath("") + "/GatherNews/gathernews/tests/"
self.path = os.path.abspath("") + "/gathernews/tests/"
self.capture_feeds = CaptureFeeds(self.path)