def test_html_body_declared_encoding(self):
fragments = [
# Content-Type as meta http-equiv
"""<meta http-equiv="content-type" content="text/html;charset=UTF-8" />""",
"""\n<meta http-equiv="Content-Type"\ncontent="text/html; charset=utf-8">""",
"""<meta content="text/html; charset=utf-8"\n http-equiv='Content-Type'>""",
""" bad html still supported < meta http-equiv='Content-Type'\n content="text/html; charset=utf-8">""",
# html5 meta charset
"""<meta charset="utf-8">""",
# xml encoding
"""<?xml version="1.0" encoding="utf-8"?>""",
]
for fragment in fragments:
encoding = html_body_declared_encoding(fragment)
self.assertEqual(encoding, 'utf-8', fragment)
self.assertEqual(None, html_body_declared_encoding("something else"))
self.assertEqual(
None,
html_body_declared_encoding("""
<head></head><body>
this isn't searched
<meta charset="utf-8">
"""))
self.assertEqual(
None,
html_body_declared_encoding(
"""<meta http-equiv="Fake-Content-Type-Header" content="text/html; charset=utf-8">"""
))
def test_html_body_declared_encoding(self):
for fragment in self.utf8_fragments:
encoding = html_body_declared_encoding(fragment)
self.assertEqual(encoding, 'utf-8', fragment)
self.assertEqual(None, html_body_declared_encoding(b"something else"))
self.assertEqual(None, html_body_declared_encoding(b"""
<head></head><body>
this isn't searched
<meta charset="utf-8">
"""))
self.assertEqual(None, html_body_declared_encoding(
b"""<meta http-equiv="Fake-Content-Type-Header" content="text/html; charset=utf-8">"""))
def test_html_body_declared_encoding(self):
for fragment in self.utf8_fragments:
encoding = html_body_declared_encoding(fragment)
self.assertEqual(encoding, 'utf-8', fragment)
self.assertEqual(None, html_body_declared_encoding(b"something else"))
self.assertEqual(None, html_body_declared_encoding(b"""
<head></head><body>
this isn't searched
<meta charset="utf-8">
"""))
self.assertEqual(None, html_body_declared_encoding(
b"""<meta http-equiv="Fake-Content-Type-Header" content="text/html; charset=utf-8">"""))
def test_html_body_declared_encoding_unicode(self):
# html_body_declared_encoding should work when unicode body is passed
self.assertEqual(None, html_body_declared_encoding(u"something else"))
for fragment in self.utf8_fragments:
encoding = html_body_declared_encoding(fragment.decode('utf8'))
self.assertEqual(encoding, 'utf-8', fragment)
self.assertEqual(None, html_body_declared_encoding(u"""
<head></head><body>
this isn't searched
<meta charset="utf-8">
"""))
self.assertEqual(None, html_body_declared_encoding(
u"""<meta http-equiv="Fake-Content-Type-Header" content="text/html; charset=utf-8">"""))
def test_html_body_declared_encoding_unicode(self):
# html_body_declared_encoding should work when unicode body is passed
self.assertEqual(None, html_body_declared_encoding(u"something else"))
for fragment in self.utf8_fragments:
encoding = html_body_declared_encoding(fragment.decode('utf8'))
self.assertEqual(encoding, 'utf-8', fragment)
self.assertEqual(None, html_body_declared_encoding(u"""
<head></head><body>
this isn't searched
<meta charset="utf-8">
"""))
self.assertEqual(None, html_body_declared_encoding(
u"""<meta http-equiv="Fake-Content-Type-Header" content="text/html; charset=utf-8">"""))
def root_node(text, encoding=None, base_url=None):
try:
text = text.read()
except AttributeError:
pass
if isinstance(text, str):
parser = html.HTMLParser(recover=True)
else:
parser = html.HTMLParser(recover=True, encoding=encoding)
try:
return etree.fromstring(
text,
parser=parser,
base_url=base_url
)
except ValueError as e:
if 'Unicode strings with encoding declaration are not supported' in str(e):
# html_body_declared_encoding may return None
encoding = html_body_declared_encoding(text) or 'utf-8'
return etree.fromstring(
text.encode(encoding),
parser=parser,
base_url=base_url
)
raise
def test_html_body_declared_encoding(self):
fragments = [
# Content-Type as meta http-equiv
"""<meta http-equiv="content-type" content="text/html;charset=UTF-8" />""",
"""\n<meta http-equiv="Content-Type"\ncontent="text/html; charset=utf-8">""",
"""<meta content="text/html; charset=utf-8"\n http-equiv='Content-Type'>""",
""" bad html still supported < meta http-equiv='Content-Type'\n content="text/html; charset=utf-8">""",
# html5 meta charset
"""<meta charset="utf-8">""",
# xml encoding
"""<?xml version="1.0" encoding="utf-8"?>""",
]
for fragment in fragments:
encoding = html_body_declared_encoding(fragment)
self.assertEqual(encoding, 'utf-8', fragment)
self.assertEqual(None, html_body_declared_encoding("something else"))
self.assertEqual(None, html_body_declared_encoding("""
<head></head><body>
this isn't searched
<meta charset="utf-8">
"""))
self.assertEqual(None, html_body_declared_encoding(
"""<meta http-equiv="Fake-Content-Type-Header" content="text/html; charset=utf-8">"""))
def _encode_or_decode_string(html, method, default):
if not default:
encoding = html_body_declared_encoding(html)
if encoding:
default = [encoding]
else:
default = []
elif isinstance(default, six.string_types):
default = [default]
for encoding in itertools.chain(default, ENCODINGS):
try:
return method(html, encoding)
except UnicodeDecodeError:
pass
encoding = chardet.detect(html).get('encoding')
return method(html, encoding)
def _encode_or_decode_string(html, method, default):
if not default:
encoding = html_body_declared_encoding(html)
if encoding:
default = [encoding]
else:
default = []
elif isinstance(default, six.string_types):
default = [default]
for encoding in itertools.chain(default, ENCODINGS):
try:
return method(html, encoding)
except (UnicodeDecodeError, UnicodeEncodeError, LookupError):
pass
except AttributeError:
return html
encoding = chardet.detect(html).get('encoding')
return method(html, encoding)
def download_url(url: str, timeout: int=None) -> str:
"""Download the contents of a remote url and return the text"""
from .config import TIMEOUT, CHECK_SSL_VALIDITY, WGET_USER_AGENT
timeout = timeout or TIMEOUT
response = requests.get(
url,
headers={'User-Agent': WGET_USER_AGENT},
verify=CHECK_SSL_VALIDITY,
timeout=timeout,
)
content_type = response.headers.get('Content-Type', '')
encoding = http_content_type_encoding(content_type) or html_body_declared_encoding(response.text)
if encoding is not None:
response.encoding = encoding
return response.text
def find_response_encoding(response):
"""
如果html的body中有charset声明的话，就会
返回相应的内容.如果没有发现，就是用chardet来估算出网页所使用的字符编码
"""
r = response.body
encoding = html_body_declared_encoding(r)
if encoding:
return encoding
else:
my_stringio = cStringIO.StringIO(r)
my_detector = UniversalDetector()
for x in my_stringio:
my_detector.feed(x)
if my_detector.done:
break
my_detector.close()
return my_detector.result['encoding']
def _body_declared_encoding(self):
return html_body_declared_encoding(self.body)
def _body_declared_encoding(cls,response):
"""
根据body 查看编码类型。
自动探测编码 是从scrapy学来的
"""
return html_body_declared_encoding(response.body)
def _body_declared_encoding(self):
return html_body_declared_encoding(self.body)
def _body_declared_encoding(cls, response):
"""
根据body 查看编码类型。
自动探测编码 是从scrapy学来的
"""
return html_body_declared_encoding(response.body)
def _body_declared_encoding(self):
"""
从html xml等获取<meta charset="编码">
"""
return html_body_declared_encoding(self.content)
