def test_download():
'''test page download and command-line interface'''
testargs = ['', '-v']
with patch.object(sys, 'argv', testargs):
args = cli.parse_args(testargs)
assert cli.examine(' ', args) is None
assert cli.examine('0' * int(10e7), args) is None
#assert utils.fetch_url('https://httpbin.org/status/404') is None
#url = 'https://httpbin.org/status/200'
#teststring = utils.fetch_url(url)
#assert teststring is None # too small
#assert cli.examine(teststring, args, url) is None
url = 'https://httpbin.org/links/2/2'
teststring = utils.fetch_url(url)
assert teststring is not None
assert cli.examine(teststring, args, url) is None
url = 'https://httpbin.org/html'
teststring = utils.fetch_url(url)
assert teststring is not None
assert cli.examine(teststring, args, url) is not None
# multiprocessing
domain_dict = dict()
domain_dict['httpbin.org'] = [
'https://httpbin.org/status/301', 'https://httpbin.org/status/304',
'https://httpbin.org/status/200', 'https://httpbin.org/status/300',
'https://httpbin.org/status/400', 'https://httpbin.org/status/500'
]
assert cli_utils.multi_threaded_processing(domain_dict, args, 0.25,
None) is None
def test_cli_pipeline():
'''test command-line processing pipeline'''
# test URL listing
testargs = ['', '--list']
with patch.object(sys, 'argv', testargs):
args = cli.parse_args(testargs)
assert cli_utils.url_processing_pipeline(args, [], 0) is None
assert cli_utils.url_processing_pipeline(
args, ['https://www.example.org/'], 0) is None
# test inputlist + blacklist
resources_dir = os.path.join(TEST_DIR, 'resources')
testargs = ['', '-i', os.path.join(resources_dir, 'list-process.txt')]
with patch.object(sys, 'argv', testargs):
args = cli.parse_args(testargs)
my_urls = cli_utils.load_input_urls(args.inputfile)
assert my_urls is not None and len(my_urls) == 2
resources_dir = os.path.join(TEST_DIR, 'resources')
#testargs = ['', '-i', os.path.join(resources_dir, 'list-process.txt'), '--blacklist', os.path.join(resources_dir, 'list-discard.txt')]
#with patch.object(sys, 'argv', testargs):
# args = cli.parse_args(testargs)
#print(args.blacklist)
#assert args.blacklist is not None
# test backoff between domain requests
reftime = datetime.now()
assert cli_utils.url_processing_pipeline(args, my_urls, 2) is None
delta = (datetime.now() - reftime).total_seconds()
assert delta > 2
# test backup
testargs = ['', '--backup-dir', '/tmp/']
with patch.object(sys, 'argv', testargs):
args = cli.parse_args(testargs)
cli_utils.archive_html('00Test', args)
cli_utils.url_processing_pipeline(args, my_urls, 2)
# test date-based exclusion
testargs = ['', '-out', 'xml', '--with-metadata']
with patch.object(sys, 'argv', testargs):
args = cli.parse_args(testargs)
with open(os.path.join(resources_dir, 'httpbin_sample.html'), 'r') as f:
teststring = f.read()
assert cli.examine(teststring, args) is None
# test timeout
testargs = ['', '-out', 'xml', '--timeout']
with patch.object(sys, 'argv', testargs):
args = cli.parse_args(testargs)
with open(os.path.join(resources_dir, 'httpbin_sample.html'), 'r') as f:
teststring = f.read()
assert cli.examine(teststring, args) is not None
# test JSON output
testargs = ['', '-out', 'json']
with patch.object(sys, 'argv', testargs):
args = cli.parse_args(testargs)
with open(os.path.join(resources_dir, 'httpbin_sample.html'), 'r') as f:
teststring = f.read()
assert cli.examine(teststring, args) is not None
# file processing pipeline
testargs = ['', '--parallel', '1', '--inputdir', '/dev/null']
with patch.object(sys, 'argv', testargs):
args = cli.parse_args(testargs)
cli_utils.file_processing_pipeline(args)
def test_download():
'''test page download and command-line interface'''
testargs = ['', '-v']
with patch.object(sys, 'argv', testargs):
args = cli.parse_args(testargs)
assert cli.examine(None, args) is None
assert cli.examine(' ', args) is None
assert cli.examine('0' * int(10e7), args) is None
#url = 'https://httpbin.org/status/200'
#teststring = utils.fetch_url(url)
#assert teststring is None # too small
#assert cli.examine(teststring, args, url) is None
#url = 'https://httpbin.org/links/2/2'
#teststring = utils.fetch_url(url)
#assert teststring is not None
#assert cli.examine(teststring, args, url) is None
url = 'https://httpbin.org/html'
teststring = utils.fetch_url(url)
assert teststring is not None
assert cli.examine(teststring, args, url) is not None
# single/multiprocessing
domain_dict = dict()
domain_dict['https://httpbin.org'] = [
'/status/301', '/status/304', '/status/200', '/status/300',
'/status/400', '/status/505'
]
args.archived = True
args.config_file = os.path.join(RESOURCES_DIR, 'newsettings.cfg')
config = use_config(filename=args.config_file)
results = cli_utils.download_queue_processing(domain_dict, args, None,
config)
assert len(results[0]) == 5 and results[1] is None
# test backoff algorithm
testdict = dict()
backoffdict = dict()
testdict['http://test.org'] = ['/1']
assert cli_utils.draw_backoff_url(testdict, backoffdict,
0, 0) == ('http://test.org/1', dict(),
dict(), 0)
testdict['http://test.org'] = ['/1']
backoffdict['test.org'] = datetime(2019, 5, 18, 15, 17, 8, 132263)
assert cli_utils.draw_backoff_url(testdict, backoffdict,
0, 0) == ('http://test.org/1', dict(),
dict(), 0)
testdict['http://test.org'] = ['/1']
backoffdict['test.org'] = datetime(2019, 5, 18, 15, 17, 8, 132263)
assert cli_utils.draw_backoff_url(testdict, backoffdict,
0, 3) == ('http://test.org/1', dict(),
dict(), 3)
testdict['http://test.org'] = ['/1']
backoffdict['test.org'] = datetime(2030, 5, 18, 15, 17, 8, 132263)
assert cli_utils.draw_backoff_url(testdict, backoffdict,
0, 3) == ('http://test.org/1', dict(),
dict(), 0)
def test_download():
'''test page download and command-line interface'''
testargs = ['', '-v']
with patch.object(sys, 'argv', testargs):
args = cli.parse_args(testargs)
assert cli.examine(None, args) is None
assert cli.examine(' ', args) is None
assert cli.examine('0' * int(10e7), args) is None
#url = 'https://httpbin.org/status/200'
#teststring = utils.fetch_url(url)
#assert teststring is None # too small
#assert cli.examine(teststring, args, url) is None
url = 'https://httpbin.org/links/2/2'
teststring = utils.fetch_url(url)
assert teststring is not None
assert cli.examine(teststring, args, url) is None
url = 'https://httpbin.org/html'
teststring = utils.fetch_url(url)
assert teststring is not None
assert cli.examine(teststring, args, url) is not None
# multiprocessing
domain_dict = dict()
domain_dict['httpbin.org'] = [
'https://httpbin.org/status/301', 'https://httpbin.org/status/304',
'https://httpbin.org/status/200', 'https://httpbin.org/status/300',
'https://httpbin.org/status/400', 'https://httpbin.org/status/505'
]
assert cli_utils.multi_threaded_processing(
domain_dict, args, 0.25,
None) == (['https://httpbin.org/status/301'], None)
# test backoff algorithm
testdict = dict()
backoffdict = dict()
testdict['test.org'] = ['http://test.org/1']
assert cli_utils.draw_backoff_url(testdict, backoffdict,
0, 0) == ('http://test.org/1', dict(),
dict(), 0)
testdict['test.org'] = ['http://test.org/1']
backoffdict['test.org'] = datetime(2019, 5, 18, 15, 17, 8, 132263)
assert cli_utils.draw_backoff_url(testdict, backoffdict,
0, 0) == ('http://test.org/1', dict(),
dict(), 0)
testdict['test.org'] = ['http://test.org/1']
backoffdict['test.org'] = datetime(2019, 5, 18, 15, 17, 8, 132263)
assert cli_utils.draw_backoff_url(testdict, backoffdict,
0, 3) == ('http://test.org/1', dict(),
dict(), 3)
testdict['test.org'] = ['http://test.org/1']
backoffdict['test.org'] = datetime(2030, 5, 18, 15, 17, 8, 132263)
assert cli_utils.draw_backoff_url(testdict, backoffdict,
0, 3) == ('http://test.org/1', dict(),
dict(), 0)
def test_input_type():
'''test input type errors'''
testfile = 'docs/trafilatura-demo.gif'
testargs = ['', '-v']
with patch.object(sys, 'argv', testargs):
args = cli.parse_args(testargs)
with open(testfile, 'rb') as f:
teststring = f.read(1024)
assert cli.examine(teststring, args) is None
testfile = 'docs/index.rst'
with open(testfile, 'r') as f:
teststring = f.read()
assert cli.examine(teststring, args) is None
def test_download():
'''test page download'''
assert utils.fetch_url('https://httpbin.org/status/404') is None
url = 'https://httpbin.org/status/200'
teststring = utils.fetch_url(url)
assert teststring is not None
assert cli.examine(teststring, url, False, True) is None
url = 'https://httpbin.org/links/2/2'
teststring = utils.fetch_url(url)
assert teststring is not None
assert cli.examine(teststring, url, False, True) is None
url = 'https://httpbin.org/html'
teststring = utils.fetch_url(url)
assert teststring is not None
assert cli.examine(teststring, url, False, True) is not None
def test_input_type():
'''test input type errors'''
testfile = 'docs/trafilatura-demo.gif'
testargs = ['', '-u', 'http']
with patch.object(sys, 'argv', testargs):
assert cli.main() is None
testargs = ['', '-v']
with patch.object(sys, 'argv', testargs):
args = cli.parse_args(testargs)
with open(testfile, 'rb') as f:
teststring = f.read(1024)
assert cli.examine(teststring, args) is None
testfile = 'docs/usage.rst'
with open(testfile, 'r') as f:
teststring = f.read()
assert cli.examine(teststring, args) is None
# test file list
assert 10 <= len(list(cli_utils.generate_filelist(RESOURCES_DIR))) <= 20
def test_input_type():
'''test input type errors'''
testfile = 'docs/trafilatura-demo.gif'
testargs = ['', '-u', 'http']
with patch.object(sys, 'argv', testargs):
assert cli.main() is None
testargs = ['', '-v']
with patch.object(sys, 'argv', testargs):
args = cli.parse_args(testargs)
with open(testfile, 'rb') as f:
teststring = f.read(1024)
assert cli.examine(teststring, args) is None
testfile = 'docs/index.rst'
with open(testfile, 'r') as f:
teststring = f.read()
assert cli.examine(teststring, args) is None
# test file list
assert cli_utils.generate_filelist(os.path.join(TEST_DIR,
'resources')) is not None
def test_download():
'''test page download and command-line interface'''
testargs = ['', '-v']
with patch.object(sys, 'argv', testargs):
args = cli.parse_args(testargs)
assert cli.examine(None, args) is None
assert cli.examine(' ', args) is None
assert cli.examine('0' * int(10e7), args) is None
#url = 'https://httpbin.org/status/200'
#teststring = fetch_url(url)
#assert teststring is None # too small
#assert cli.examine(teststring, args, url) is None
#url = 'https://httpbin.org/links/2/2'
#teststring = fetch_url(url)
#assert teststring is not None
#assert cli.examine(teststring, args, url) is None
url = 'https://httpbin.org/html'
teststring = fetch_url(url)
assert teststring is not None
assert cli.examine(teststring, args, url) is not None
def test_cli_pipeline():
'''test command-line processing pipeline'''
# straight command-line input
#testargs = ['', '<html><body>Text</body></html>']
#with patch.object(sys, 'argv', testargs):
# args = cli.parse_args(testargs)
#f = io.StringIO()
#with redirect_stdout(f):
# cli.process_args(args)
#assert len(f.getvalue()) == 0
# test URL listing
# Force encoding to utf-8 for Windows in future processes spawned by multiprocessing.Pool
os.environ['PYTHONIOENCODING'] = "utf-8"
testargs = ['', '--list']
with patch.object(sys, 'argv', testargs):
args = cli.parse_args(testargs)
assert cli_utils.url_processing_pipeline(args, dict()) is None
# test inputlist + blacklist
testargs = ['', '-i', os.path.join(RESOURCES_DIR, 'list-process.txt')]
with patch.object(sys, 'argv', testargs):
args = cli.parse_args(testargs)
my_urls = cli_utils.load_input_urls(args)
assert my_urls is not None and len(my_urls) == 2
testargs = [
'', '-i',
os.path.join(RESOURCES_DIR, 'list-process.txt'), '--blacklist',
os.path.join(RESOURCES_DIR, 'list-discard.txt'), '--archived'
]
with patch.object(sys, 'argv', testargs):
args = cli.parse_args(testargs)
assert args.blacklist is not None
# test backoff between domain requests
inputdict = add_to_compressed_dict(my_urls, args.blacklist, None, None)
reftime = datetime.now()
cli_utils.url_processing_pipeline(args, inputdict)
delta = (datetime.now() - reftime).total_seconds()
assert delta > 2
# test blacklist and empty dict
args.blacklist = cli_utils.load_blacklist(args.blacklist)
assert len(args.blacklist) == 2
inputdict = add_to_compressed_dict(my_urls, args.blacklist, None, None)
cli_utils.url_processing_pipeline(args, inputdict)
# test backup
testargs = ['', '--backup-dir', '/tmp/']
with patch.object(sys, 'argv', testargs):
args = cli.parse_args(testargs)
cli_utils.archive_html('00Test', args)
# test date-based exclusion
testargs = ['', '-out', 'xml', '--with-metadata']
with patch.object(sys, 'argv', testargs):
args = cli.parse_args(testargs)
with open(os.path.join(RESOURCES_DIR, 'httpbin_sample.html'), 'r') as f:
teststring = f.read()
assert cli.examine(teststring, args) is None
testargs = ['', '-out', 'xml', '--only-with-metadata', '--precision']
with patch.object(sys, 'argv', testargs):
args = cli.parse_args(testargs)
with open(os.path.join(RESOURCES_DIR, 'httpbin_sample.html'), 'r') as f:
teststring = f.read()
assert cli.examine(teststring, args) is None
# test JSON output
testargs = ['', '-out', 'json', '--recall']
with patch.object(sys, 'argv', testargs):
args = cli.parse_args(testargs)
with open(os.path.join(RESOURCES_DIR, 'httpbin_sample.html'), 'r') as f:
teststring = f.read()
assert cli.examine(teststring, args) is not None
# dry-run file processing pipeline
testargs = ['', '--parallel', '1', '--inputdir', '/dev/null']
with patch.object(sys, 'argv', testargs):
args = cli.parse_args(testargs)
cli_utils.file_processing_pipeline(args)
# file processing pipeline on resources/
args.inputdir = RESOURCES_DIR
cli_utils.file_processing_pipeline(args)
# sitemaps
testargs = ['', '--sitemap', 'https://httpbin.org/', '--list']
with patch.object(sys, 'argv', testargs):
args = cli.parse_args(testargs)
f = io.StringIO()
with redirect_stdout(f):
cli.process_args(args)
assert len(f.getvalue()) == 0
# config file
testargs = [
'', '--inputdir', '/dev/null', '--config-file', 'newsettings.cfg'
]
with patch.object(sys, 'argv', testargs):
args = cli.parse_args(testargs)
with open(os.path.join(RESOURCES_DIR, 'httpbin_sample.html'), 'r') as f:
teststring = f.read()
args.config_file = os.path.join(RESOURCES_DIR, args.config_file)
# config = use_config(filename=args.config_file)
assert cli.examine(teststring, args) is None
# CLI options
testargs = ['', '--links', '--images']
with patch.object(sys, 'argv', testargs):
args = cli.parse_args(testargs)
#with open(os.path.join(RESOURCES_DIR, 'http_sample.html'), 'r') as f:
# teststring = f.read()
#result = cli.examine(teststring, args)
#assert '[link](testlink.html)' in result # and 'test.jpg' in result
# Crawling
testargs = ['', '--crawl', 'https://httpbin.org/html']
with patch.object(sys, 'argv', testargs):
args = cli.parse_args(testargs)
f = io.StringIO()
with redirect_stdout(f):
cli_utils.cli_crawler(args)
assert len(f.getvalue()) == 0
# links permitted
testargs = [
'', '--crawl', 'https://httpbin.org/links/1/1', '--list', '--parallel',
'1'
]
with patch.object(sys, 'argv', testargs):
args = cli.parse_args(testargs)
f = io.StringIO()
with redirect_stdout(f):
cli_utils.cli_crawler(args)
assert f.getvalue() == 'https://httpbin.org/links/1/0\n'
# 0 links permitted
args.crawl = 'https://httpbin.org/links/4/4'
f = io.StringIO()
with redirect_stdout(f):
cli_utils.cli_crawler(args, n=0)
# print(f.getvalue())
assert len(f.getvalue().split('\n')) == 5
# Exploration (Sitemap + Crawl)
testargs = ['', '--explore', 'https://httpbin.org/html']
with patch.object(sys, 'argv', testargs):
args = cli.parse_args(testargs)
f = io.StringIO()
with redirect_stdout(f):
cli.process_args(args)
assert len(f.getvalue()) == 0
def test_cli_pipeline():
'''test command-line processing pipeline'''
# straight command-line input
#testargs = ['', '<html><body>Text</body></html>']
#with patch.object(sys, 'argv', testargs):
# args = cli.parse_args(testargs)
#f = io.StringIO()
#with redirect_stdout(f):
# cli.process_args(args)
#assert len(f.getvalue()) == 0
# test URL listing
testargs = ['', '--list']
with patch.object(sys, 'argv', testargs):
args = cli.parse_args(testargs)
assert cli_utils.url_processing_pipeline(args, dict()) is None
# test conversion and storage
inputdict = cli.convert_inputlist(None, ['ftps://www.example.org/'], None,
None)
assert inputdict == dict()
inputdict = cli.convert_inputlist(None, ['https://www.example.org/'], None,
None)
assert cli_utils.url_processing_pipeline(args, inputdict) is None
# test inputlist + blacklist
testargs = ['', '-i', os.path.join(RESOURCES_DIR, 'list-process.txt')]
with patch.object(sys, 'argv', testargs):
args = cli.parse_args(testargs)
my_urls = cli_utils.load_input_urls(args.inputfile)
assert my_urls is not None and len(my_urls) == 2
testargs = [
'', '-i',
os.path.join(RESOURCES_DIR, 'list-process.txt'), '--blacklist',
os.path.join(RESOURCES_DIR, 'list-discard.txt'), '--archived'
]
with patch.object(sys, 'argv', testargs):
args = cli.parse_args(testargs)
assert args.blacklist is not None
# test backoff between domain requests
inputdict = cli_utils.convert_inputlist(args.blacklist, my_urls, None,
None)
reftime = datetime.now()
cli_utils.url_processing_pipeline(args, inputdict)
delta = (datetime.now() - reftime).total_seconds()
assert delta > 2
# test blacklist and empty dict
args.blacklist = cli_utils.load_blacklist(args.blacklist)
assert len(args.blacklist) == 2
inputdict = cli_utils.convert_inputlist(args.blacklist, my_urls, None,
None)
cli_utils.url_processing_pipeline(args, inputdict)
# test backup
testargs = ['', '--backup-dir', '/tmp/']
with patch.object(sys, 'argv', testargs):
args = cli.parse_args(testargs)
cli_utils.archive_html('00Test', args)
# test date-based exclusion
testargs = ['', '-out', 'xml', '--with-metadata']
with patch.object(sys, 'argv', testargs):
args = cli.parse_args(testargs)
with open(os.path.join(RESOURCES_DIR, 'httpbin_sample.html'), 'r') as f:
teststring = f.read()
assert cli.examine(teststring, args) is None
# test JSON output
testargs = ['', '-out', 'json']
with patch.object(sys, 'argv', testargs):
args = cli.parse_args(testargs)
with open(os.path.join(RESOURCES_DIR, 'httpbin_sample.html'), 'r') as f:
teststring = f.read()
assert cli.examine(teststring, args) is not None
# dry-run file processing pipeline
testargs = ['', '--parallel', '1', '--inputdir', '/dev/null']
with patch.object(sys, 'argv', testargs):
args = cli.parse_args(testargs)
cli_utils.file_processing_pipeline(args)
# file processing pipeline on resources/
args.inputdir = RESOURCES_DIR
cli_utils.file_processing_pipeline(args)
# sitemaps
testargs = ['', '--sitemap', 'https://httpbin.org/', '--list']
with patch.object(sys, 'argv', testargs):
args = cli.parse_args(testargs)
f = io.StringIO()
with redirect_stdout(f):
cli.process_args(args)
assert len(f.getvalue()) == 0
# config file
testargs = [
'', '--inputdir', '/dev/null', '--config-file', 'newsettings.cfg'
]
with patch.object(sys, 'argv', testargs):
args = cli.parse_args(testargs)
with open(os.path.join(RESOURCES_DIR, 'httpbin_sample.html'), 'r') as f:
teststring = f.read()
args.config_file = os.path.join(RESOURCES_DIR, args.config_file)
config = use_config(filename=args.config_file)
assert cli.examine(teststring, args) is None
# CLI options
testargs = ['', '--links', '--images']
with patch.object(sys, 'argv', testargs):
args = cli.parse_args(testargs)
