import unittest
from scrapy.responsetypes import responsetypes
from scrapy.http import Response, TextResponse, XmlResponse, HtmlResponse, Headers
class ResponseTypesTest(unittest.TestCase):
def test_from_filename(self):
mappings = [
('data.bin', Response),
('file.txt', TextResponse),
('file.xml.gz', Response),
('file.xml', XmlResponse),
('file.html', HtmlResponse),
('file.unknownext', Response),
]
for source, cls in mappings:
retcls = responsetypes.from_filename(source)
assert retcls is cls, f"{source} ==> {retcls} != {cls}"
def test_from_content_disposition(self):
mappings = [
(b'attachment; filename="data.xml"', XmlResponse),
(b'attachment; filename=data.xml', XmlResponse),
('attachment;filename=data£.tar.gz'.encode('utf-8'), Response),
('attachment;filename=dataµ.tar.gz'.encode('latin-1'), Response),
('attachment;filename=data高.doc'.encode('gbk'), Response),
('attachment;filename=دورهdata.html'.encode('cp720'), HtmlResponse),
('attachment;filename=日本語版Wikipedia.xml'.encode('iso2022_jp'), XmlResponse),
]
for source, cls in mappings:
retcls = responsetypes.from_content_disposition(source)
assert retcls is cls, f"{source} ==> {retcls} != {cls}"
def test_from_content_type(self):
mappings = [
('text/html; charset=UTF-8', HtmlResponse),
('text/xml; charset=UTF-8', XmlResponse),
('application/xhtml+xml; charset=UTF-8', HtmlResponse),
('application/vnd.wap.xhtml+xml; charset=utf-8', HtmlResponse),
('application/xml; charset=UTF-8', XmlResponse),
('application/octet-stream', Response),
('application/x-json; encoding=UTF8;charset=UTF-8', TextResponse),
('application/json-amazonui-streaming;charset=UTF-8', TextResponse),
]
for source, cls in mappings:
retcls = responsetypes.from_content_type(source)
assert retcls is cls, f"{source} ==> {retcls} != {cls}"
def test_from_body(self):
mappings = [
(b'\x03\x02\xdf\xdd\x23', Response),
(b'Some plain text\ndata with tabs\t and null bytes\0', TextResponse),
(b'Hello', HtmlResponse),
(b' {retcls} != {cls}"
def test_from_headers(self):
mappings = [
({'Content-Type': ['text/html; charset=utf-8']}, HtmlResponse),
({'Content-Type': ['text/html; charset=utf-8'], 'Content-Encoding': ['gzip']}, Response),
({'Content-Type': ['application/octet-stream'],
'Content-Disposition': ['attachment; filename=data.txt']}, TextResponse),
]
for source, cls in mappings:
source = Headers(source)
retcls = responsetypes.from_headers(source)
assert retcls is cls, f"{source} ==> {retcls} != {cls}"
def test_from_args_pre_xtractmime(self):
mappings = [
({'url': 'http://www.example.com/data.csv'}, TextResponse),
({'headers': Headers({'Content-Type': ['text/html; charset=utf-8']}),
'url': 'http://www.example.com/item/'}, HtmlResponse), # Failing with xtractmime, returning TextResponse expected HtmlResponse
({'headers': Headers({'Content-Disposition': ['attachment; filename="data.xml.gz"']}),
'url': 'http://www.example.com/page/'}, Response), # Failing with xtractmime, returning TextResponse expected Response
]
for source, cls in mappings:
retcls = responsetypes.from_args(**source)
assert retcls is cls, f"{source} ==> {retcls} != {cls}"
def test_from_args_post_xtractmime(self):
mappings = [
({'body': b'Some plain text data with tabs and null bytes'}, TextResponse),
({'body': b'\x03\x02\xdf\xdd\x23', 'headers': Headers({'Content-Encoding': 'UTF-8'})},
Response),
# different behaviour with http and non-http urls
({'body': b'\x00\xfe\xff', 'url': 'http://www.example.com/item/',
'headers': Headers({'Content-Type': b'text/plain'})}, Response),
({'body': b'\x00\xfe\xff', 'url': '://www.example.com/item/',
'headers': Headers({'Content-Type': b'text/plain'})}, TextResponse),
({'url': 'http://www.example.com/item/file.html'}, HtmlResponse), # Failing with xtractmime, return TextResponse expected HtmlResponse
({'body': b'Some plain text\ndata with tabs\t and null bytes\0'}, Response), # earlier expected to be binary response, refer "test_from_body()"
({'body': b'Hello'}, HtmlResponse),
({'body': b' {retcls} != {cls}"
def test_custom_mime_types_loaded(self):
# check that mime.types files shipped with scrapy are loaded
self.assertEqual(responsetypes.mimetypes.guess_type('x.scrapytest')[0], 'x-scrapy/test')
if __name__ == "__main__":
unittest.main()