def open(self, url, **params):
if url.startswith('http') and params:
r = requests.get(url, params=params, stream=True)
r.raw.decode_content = self.decode
response = r.text if self.cache_type else r.raw
else:
try:
r = urlopen(url, context=self.context, timeout=self.timeout)
except TypeError:
r = urlopen(url, timeout=self.timeout)
text = r.read() if self.cache_type else None
if self.decode:
encoding = get_response_encoding(r, self.def_encoding)
if text:
response = decode(text, encoding)
else:
response = reencode(r.fp, encoding, decode=True)
else:
response = text or r
content_type = get_response_content_type(r)
if 'xml' in content_type:
self.ext = 'xml'
elif 'json' in content_type:
self.ext = 'json'
else:
self.ext = content_type.split('/')[1].split(';')[0]
self.r = r
return response
def open(self, url, **params):
if url.startswith('http') and params:
r = requests.get(url, params=params, stream=True)
r.raw.decode_content = self.decode
response = r.text if self.cache_type else r.raw
else:
try:
r = urlopen(url, context=self.context, timeout=self.timeout)
except TypeError:
r = urlopen(url, timeout=self.timeout)
text = r.read() if self.cache_type else None
if self.decode:
encoding = get_response_encoding(r, self.def_encoding)
if self.cache_type:
response = decode(text, encoding)
else:
response = reencode(r.fp, encoding, decode=True)
else:
response = text if self.cache_type else r
self.r = r
return response
def test_reencode(self):
file_ = p.join(io.DATA_DIR, "utf16_big.csv")
with open(file_, encoding="utf-16-be") as f:
utf8_f = io.reencode(f, remove_BOM=True)
nt.assert_equal(b"a,b,c", next(utf8_f).strip())
nt.assert_equal(b"1,2,3", next(utf8_f).strip())
nt.assert_equal("4,5,ʤ", next(utf8_f).decode("utf-8"))
def test_reencode(self):
file_ = p.join(io.DATA_DIR, 'utf16_big.csv')
with open(file_, encoding='utf-16-be') as f:
utf8_f = io.reencode(f, remove_BOM=True)
nt.assert_equal(b'a,b,c', next(utf8_f).strip())
nt.assert_equal(b'1,2,3', next(utf8_f).strip())
nt.assert_equal('4,5,ʤ', next(utf8_f).decode('utf-8'))
def opener(url,
memoize=False,
delay=0,
encoding=ENCODING,
params=None,
**kwargs):
params = params or {}
timeout = kwargs.get('timeout')
decode = kwargs.get('decode')
if url.startswith('http') and params:
r = requests.get(url, params=params, stream=True)
r.raw.decode_content = decode
response = r.text if memoize else r.raw
else:
req = Request(url, headers={'User-Agent': default_user_agent()})
context = SleepyDict(delay=delay) if delay else None
try:
r = urlopen(req, context=context, timeout=timeout)
except TypeError:
r = urlopen(req, timeout=timeout)
except HTTPError as e:
raise URLError(f'{url} returned {e.code}: {e.reason}')
except URLError as e:
raise URLError(f'{url}: {e.reason}')
text = r.read() if memoize else None
if decode:
encoding = get_response_encoding(r, encoding)
if text:
response = compat.decode(text, encoding)
else:
response = reencode(r.fp, encoding, decode=True)
response.r = r
else:
response = text or r
content_type = get_response_content_type(r)
return (response, content_type)
def open(self, url, **params):
if url.startswith('http') and params:
r = requests.get(url, params=params, stream=True)
r.raw.decode_content = self.decode
response = r.text if self.cache_type else r.raw
else:
req = Request(url, headers={'User-Agent': default_user_agent()})
try:
r = urlopen(req, context=self.context, timeout=self.timeout)
except TypeError:
r = urlopen(req, timeout=self.timeout)
except HTTPError as e:
msg = '{} returned {}: {}'
raise URLError(msg.format(url, e.code, e.reason))
except URLError as e:
raise URLError('{}: {}'.format(url, e.reason))
text = r.read() if self.cache_type else None
if self.decode:
encoding = get_response_encoding(r, self.def_encoding)
if text:
response = decode(text, encoding)
else:
response = reencode(r.fp, encoding, decode=True)
else:
response = text or r
content_type = get_response_content_type(r)
if 'xml' in content_type:
self.ext = 'xml'
elif 'json' in content_type:
self.ext = 'json'
else:
self.ext = content_type.split('/')[1].split(';')[0]
self.r = r
return response
def open(self, url, **params):
if url.startswith('http') and params:
r = requests.get(url, params=params, stream=True)
r.raw.decode_content = self.decode
response = r.text if self.cache_type else r.raw
else:
try:
r = urlopen(url, context=self.context, timeout=self.timeout)
except TypeError:
r = urlopen(url, timeout=self.timeout)
except HTTPError as e:
msg = '{} returned {}: {}'
raise URLError(msg.format(url, e.code, e.reason))
except URLError as e:
raise URLError('{}: {}'.format(url, e.reason))
text = r.read() if self.cache_type else None
if self.decode:
encoding = get_response_encoding(r, self.def_encoding)
if text:
response = decode(text, encoding)
else:
response = reencode(r.fp, encoding, decode=True)
else:
response = text or r
content_type = get_response_content_type(r)
if 'xml' in content_type:
self.ext = 'xml'
elif 'json' in content_type:
self.ext = 'json'
else:
self.ext = content_type.split('/')[1].split(';')[0]
self.r = r
return response
