def test_css_converter(self):
url_table = URLTable()
css_filename = os.path.join(self.temp_dir.name, 'styles.css')
image_filename = os.path.join(self.temp_dir.name, 'image.png')
new_css_filename = os.path.join(self.temp_dir.name, 'styles.css-new')
url_table.add_many([
{'url': 'http://example.com/styles.css'},
{'url': 'http://example.com/image.png'},
{'url': 'http://example.com/cat.jpg'},
{'url': 'http://example.com/cat.jpg'},
])
url_table.update_one(
'http://example.com/styles.css',
status=Status.done,
link_type='css',
filename=os.path.relpath(css_filename, self.temp_dir.name)
)
url_table.update_one(
'http://example.com/image.png',
status=Status.done,
filename=os.path.relpath(image_filename, self.temp_dir.name)
)
with open(css_filename, 'w') as out_file:
out_file.write(CSS_TEXT)
with open(image_filename, 'wb'):
pass
converter = CSSConverter(url_table)
converter.convert(
css_filename, new_css_filename,
base_url='http://example.com/styles.css'
)
with open(new_css_filename, 'r') as in_file:
converted_text = in_file.read()
self.assertIn("url('image.png')", converted_text)
self.assertIn("url('http://example.com/cat.jpg')", converted_text)
def test_css_converter(self):
url_table = URLTable()
css_filename = os.path.join(self.temp_dir.name, "styles.css")
image_filename = os.path.join(self.temp_dir.name, "image.png")
new_css_filename = os.path.join(self.temp_dir.name, "styles.css-new")
url_table.add_many(
[
AddURLInfo("http://example.com/styles.css", None, None),
AddURLInfo("http://example.com/image.png", None, None),
AddURLInfo("http://example.com/cat.jpg", None, None),
AddURLInfo("http://example.com/cat.jpg", None, None),
]
)
url_table.update_one(
"http://example.com/styles.css",
status=Status.done.value,
link_type="css",
filename=os.path.relpath(css_filename, self.temp_dir.name),
)
url_table.update_one(
"http://example.com/image.png",
status=Status.done.value,
filename=os.path.relpath(image_filename, self.temp_dir.name),
)
with open(css_filename, "w") as out_file:
out_file.write(CSS_TEXT)
with open(image_filename, "wb"):
pass
converter = CSSConverter(url_table)
converter.convert(css_filename, new_css_filename, base_url="http://example.com/styles.css")
with open(new_css_filename, "r") as in_file:
converted_text = in_file.read()
self.assertIn("url('image.png')", converted_text)
self.assertIn("url('http://example.com/cat.jpg')", converted_text)
def test_xhtml_converter(self):
url_table = URLTable()
image_filename = os.path.join(self.temp_dir.name, 'image.png')
tubes_filename = os.path.join(self.temp_dir.name, 'tubes.html')
ferret_filename = os.path.join(self.temp_dir.name, 'ferret.jpg')
url_table.add_many([
{'url': 'http://example.com/styles.css'},
{'url': 'http://example.com/image.png'},
{'url': 'http://example.com/cat.jpg'},
{'url': 'http://example.com/fox.jpg'},
{'url': 'http://example.com/ferret.jpg'},
{'url': 'http://example.com/tubes.html'},
])
url_table.update_one(
'http://example.com/styles.css',
status=Status.done,
link_type='css'
)
url_table.update_one(
'http://example.com/image.png',
status=Status.done,
filename=os.path.relpath(image_filename, self.temp_dir.name)
)
url_table.update_one(
'http://example.com/tubes.html',
status=Status.done,
filename=os.path.relpath(tubes_filename, self.temp_dir.name)
)
url_table.update_one(
'http://example.com/ferret.jpg',
status=Status.done,
filename=os.path.relpath(ferret_filename, self.temp_dir.name)
)
html_filename = os.path.join(self.temp_dir.name, 'index.html')
new_html_filename = os.path.join(self.temp_dir.name, 'index.html-new')
with open(html_filename, 'w') as out_file:
out_file.write(XHTML_TEXT)
for filename in [image_filename, tubes_filename, ferret_filename]:
with open(filename, 'wb'):
pass
element_walker = ElementWalker(css_scraper=CSSScraper())
converter = HTMLConverter(
self.get_html_parser(), element_walker, url_table)
converter.convert(
html_filename, new_html_filename,
base_url='http://example.com/index.html'
)
with open(new_html_filename, 'r') as in_file:
converted_text = in_file.read()
self.assertIn("url('image.png')", converted_text)
self.assertIn("url('http://example.com/cat.jpg')", converted_text)
self.assertIn('"tubes.html"', converted_text)
self.assertIn('"http://example.com/lol.html"', converted_text)
self.assertIn("url('http://example.com/fox.jpg')", converted_text)
self.assertIn("url('ferret.jpg')", converted_text)
self.assertIn("hello world!!", converted_text)
self.assertIn("<hr/>", converted_text)
def test_xhtml_converter(self):
url_table = URLTable()
image_filename = os.path.join(self.temp_dir.name, "image.png")
tubes_filename = os.path.join(self.temp_dir.name, "tubes.html")
ferret_filename = os.path.join(self.temp_dir.name, "ferret.jpg")
url_table.add_many(
[
AddURLInfo("http://example.com/styles.css", None, None),
AddURLInfo("http://example.com/image.png", None, None),
AddURLInfo("http://example.com/cat.jpg", None, None),
AddURLInfo("http://example.com/fox.jpg", None, None),
AddURLInfo("http://example.com/ferret.jpg", None, None),
AddURLInfo("http://example.com/tubes.html", None, None),
]
)
url_table.update_one("http://example.com/styles.css", status=Status.done.value, link_type="css")
url_table.update_one(
"http://example.com/image.png",
status=Status.done.value,
filename=os.path.relpath(image_filename, self.temp_dir.name),
)
url_table.update_one(
"http://example.com/tubes.html",
status=Status.done.value,
filename=os.path.relpath(tubes_filename, self.temp_dir.name),
)
url_table.update_one(
"http://example.com/ferret.jpg",
status=Status.done.value,
filename=os.path.relpath(ferret_filename, self.temp_dir.name),
)
html_filename = os.path.join(self.temp_dir.name, "index.html")
new_html_filename = os.path.join(self.temp_dir.name, "index.html-new")
with open(html_filename, "w") as out_file:
out_file.write(XHTML_TEXT)
for filename in [image_filename, tubes_filename, ferret_filename]:
with open(filename, "wb"):
pass
element_walker = ElementWalker(css_scraper=CSSScraper())
converter = HTMLConverter(self.get_html_parser(), element_walker, url_table)
converter.convert(html_filename, new_html_filename, base_url="http://example.com/index.html")
with open(new_html_filename, "r") as in_file:
converted_text = in_file.read()
self.assertIn("url('image.png')", converted_text)
self.assertIn("url('http://example.com/cat.jpg')", converted_text)
self.assertIn('"tubes.html"', converted_text)
self.assertIn('"http://example.com/lol.html"', converted_text)
self.assertIn("url('http://example.com/fox.jpg')", converted_text)
self.assertIn("url('ferret.jpg')", converted_text)
self.assertIn("hello world!!", converted_text)
self.assertIn("<hr/>", converted_text)
def test_cdx_dedup(self):
url_table = URLTable()
warc_recorder = WARCRecorder('asdf',
params=WARCRecorderParams(
compress=False,
cdx=True,
url_table=url_table))
url_table.add_visits([
('http://example.com/fennec',
'<urn:uuid:8a534d31-bd06-4056-8a0f-bdc5fd611036>',
'B62D734VFEKIDLFAB7TTSCSZF64BKAYJ')
])
request = HTTPRequest('http://example.com/fennec')
request.address = ('0.0.0.0', 80)
response = HTTPResponse(200, 'OK')
response.body = Body()
revisit_response_header_size = len(response.to_bytes())
with wpull.util.reset_file_offset(response.body):
response.body.write(b'kitbit')
with warc_recorder.session() as session:
session.pre_request(request)
session.request_data(request.to_bytes())
session.request(request)
session.pre_response(response)
session.response_data(response.to_bytes())
session.response_data(response.body.content())
session.response(response)
request = HTTPRequest('http://example.com/horse')
request.address = ('0.0.0.0', 80)
response = HTTPResponse(200, 'OKaaaaaaaaaaaaaaaaaaaaaaaaaa')
response.body = Body()
with wpull.util.reset_file_offset(response.body):
response.body.write(b'kitbit')
with warc_recorder.session() as session:
session.pre_request(request)
session.request_data(request.to_bytes())
session.request(request)
session.pre_response(response)
session.response_data(response.to_bytes())
session.response_data(response.body.content())
session.response(response)
_logger.info('FINISHED')
warc_recorder.close()
with open('asdf.warc', 'rb') as in_file:
warc_file_content = in_file.read()
with open('asdf.cdx', 'rb') as in_file:
cdx_file_content = in_file.read()
self.assertTrue(warc_file_content.startswith(b'WARC/1.0'))
self.assertIn(b'WARC-Type: revisit\r\n', warc_file_content)
self.assertIn(
b'WARC-Refers-To: '
b'<urn:uuid:8a534d31-bd06-4056-8a0f-bdc5fd611036>\r\n',
warc_file_content)
self.assertIn(b'WARC-Truncated: length\r\n', warc_file_content)
self.assertIn(
b'WARC-Profile: http://netpreserve.org/warc/1.0/revisit/'
b'identical-payload-digest\r\n', warc_file_content)
self.assertIn(
b'Content-Length: ' +
str(revisit_response_header_size).encode('ascii') + b'\r\n',
warc_file_content)
self.assertIn(b'WARC-Target-URI: http://example.com/fennec\r\n',
warc_file_content)
self.assertIn(b'WARC-Target-URI: http://example.com/horse\r\n',
warc_file_content)
self.assertEqual(1, warc_file_content.count(b'kitbit'))
self.assertIn(b'http://example.com/horse ', cdx_file_content)
def test_cdx_dedup(self):
url_table = URLTable()
warc_recorder = WARCRecorder(
'asdf',
params=WARCRecorderParams(
compress=False, cdx=True, url_table=url_table
)
)
url_table.add_visits([
(
'http://example.com/fennec',
'<urn:uuid:8a534d31-bd06-4056-8a0f-bdc5fd611036>',
'B62D734VFEKIDLFAB7TTSCSZF64BKAYJ'
)
])
request = HTTPRequest('http://example.com/fennec')
request.address = ('0.0.0.0', 80)
response = HTTPResponse(200, 'OK')
response.body = Body()
revisit_response_header_size = len(response.to_bytes())
with wpull.util.reset_file_offset(response.body):
response.body.write(b'kitbit')
session = warc_recorder.new_http_recorder_session()
session.begin_request(request)
session.request_data(request.to_bytes())
session.end_request(request)
session.begin_response(response)
session.response_data(response.to_bytes())
session.response_data(response.body.content())
session.end_response(response)
session.close()
request = HTTPRequest('http://example.com/horse')
request.address = ('0.0.0.0', 80)
response = HTTPResponse(200, 'OKaaaaaaaaaaaaaaaaaaaaaaaaaa')
response.body = Body()
with wpull.util.reset_file_offset(response.body):
response.body.write(b'kitbit')
session = warc_recorder.new_http_recorder_session()
session.begin_request(request)
session.request_data(request.to_bytes())
session.end_request(request)
session.begin_response(response)
session.response_data(response.to_bytes())
session.response_data(response.body.content())
session.end_response(response)
session.close()
_logger.info('FINISHED')
warc_recorder.close()
with open('asdf.warc', 'rb') as in_file:
warc_file_content = in_file.read()
with open('asdf.cdx', 'rb') as in_file:
cdx_file_content = in_file.read()
self.assertTrue(warc_file_content.startswith(b'WARC/1.0'))
self.assertIn(b'WARC-Type: revisit\r\n', warc_file_content)
self.assertIn(
b'WARC-Refers-To: '
b'<urn:uuid:8a534d31-bd06-4056-8a0f-bdc5fd611036>\r\n',
warc_file_content
)
self.assertIn(b'WARC-Truncated: length\r\n', warc_file_content)
self.assertIn(
b'WARC-Profile: http://netpreserve.org/warc/1.0/revisit/'
b'identical-payload-digest\r\n',
warc_file_content
)
self.assertIn(
b'Content-Length: ' +
str(revisit_response_header_size).encode('ascii') + b'\r\n',
warc_file_content
)
self.assertIn(
b'WARC-Target-URI: http://example.com/fennec\r\n',
warc_file_content
)
self.assertIn(
b'WARC-Target-URI: http://example.com/horse\r\n', warc_file_content
)
self.assertEqual(
1,
warc_file_content.count(b'kitbit')
)
self.assertIn(b'http://example.com/horse ', cdx_file_content)
