本文整理汇总了Python中talon.quotations.extract_from_html函数的典型用法代码示例。如果您正苦于以下问题：Python extract_from_html函数的具体用法？Python extract_from_html怎么用？Python extract_from_html使用的例子？那么恭喜您, 这里精选的函数代码示例或许可以为您提供帮助。
在下文中一共展示了extract_from_html函数的20个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于我们的系统推荐出更棒的Python代码示例。
示例1: test_CRLF
def test_CRLF():
"""CR is not converted to ' '
"""
symbol = ' '
extracted = quotations.extract_from_html('<html>\r\n</html>')
assert_false(symbol in extracted)
eq_('<html></html>', RE_WHITESPACE.sub('', extracted))
msg_body = """My
reply
<blockquote>
<div>
On 11-Apr-2011, at 6:54 PM, Bob <[email protected]> wrote:
</div>
<div>
Test
</div>
</blockquote>"""
msg_body = msg_body.replace('\n', '\r\n')
extracted = quotations.extract_from_html(msg_body)
assert_false(symbol in extracted)
# Keep new lines otherwise "My reply" becomes one word - "Myreply"
eq_("<html><head></head><body>My\nreply\n</body></html>", extracted)
开发者ID:guruhq，项目名称:talon，代码行数:26，代码来源:html_quotations_test.py
示例2: test_no_blockquote
def test_no_blockquote():
msg_body = """
<html>
<body>
Reply
<div>
On 11-Apr-2011, at 6:54 PM, Bob <[email protected]> wrote:
</div>
<div>
Test
</div>
</body>
</html>
"""
reply = """
<html>
<head></head>
<body>
Reply
</body></html>"""
eq_(RE_WHITESPACE.sub('', reply),
RE_WHITESPACE.sub('', quotations.extract_from_html(msg_body)))
开发者ID:guruhq，项目名称:talon，代码行数:26，代码来源:html_quotations_test.py
示例3: test_blockquote_disclaimer
def test_blockquote_disclaimer():
msg_body = """
<html>
<body>
<div>
<div>
message
</div>
<blockquote>
Quote
</blockquote>
</div>
<div>
disclaimer
</div>
</body>
</html>
"""
stripped_html = """
<html>
<body>
<div>
<div>
message
</div>
</div>
<div>
disclaimer
</div>
</body>
</html>
"""
eq_(RE_WHITESPACE.sub('', stripped_html),
RE_WHITESPACE.sub('', quotations.extract_from_html(msg_body)))
开发者ID:clara-labs，项目名称:talon，代码行数:35，代码来源:html_quotations_test.py
示例4: test_reply_quotations_share_block
def test_reply_quotations_share_block():
msg = mime.from_string(REPLY_QUOTATIONS_SHARE_BLOCK)
html_part = list(msg.walk())[1]
assert html_part.content_type == 'text/html'
stripped_html = quotations.extract_from_html(html_part.body)
ok_(stripped_html)
ok_('From' not in stripped_html)
开发者ID:CatalinBraescu，项目名称:talon，代码行数:7，代码来源:html_quotations_test.py
示例5: test_gmail_quote_compact
def test_gmail_quote_compact():
msg_body = 'Reply' \
'<div class="gmail_quote">' \
'<div class="gmail_quote">On 11-Apr-2011, at 6:54 PM, Bob <[email protected]> wrote:' \
'<div>Test</div>' \
'</div>' \
'</div>'
eq_("<html><head></head><body>Reply</body></html>",
RE_WHITESPACE.sub('', quotations.extract_from_html(msg_body)))
开发者ID:guruhq，项目名称:talon，代码行数:9，代码来源:html_quotations_test.py
示例6: extract_reply_and_check
def extract_reply_and_check(filename):
f = open(filename)
msg_body = f.read()
reply = quotations.extract_from_html(msg_body)
plain_reply = u.html_to_text(reply)
eq_(RE_WHITESPACE.sub('', "Hi. I am fine.\n\nThanks,\nAlex"),
RE_WHITESPACE.sub('', plain_reply))
开发者ID:dichen001，项目名称:talon，代码行数:9，代码来源:html_quotations_test.py
示例7: test_too_large_html
def test_too_large_html():
msg_body = 'Reply' \
'<div class="gmail_quote">' \
'<div class="gmail_quote">On 11-Apr-2011, at 6:54 PM, Bob <[email protected]> wrote:' \
'<div>Test</div>' \
'</div>' \
'</div>'
eq_(RE_WHITESPACE.sub('', msg_body),
RE_WHITESPACE.sub('', quotations.extract_from_html(msg_body)))
开发者ID:guruhq，项目名称:talon，代码行数:9，代码来源:html_quotations_test.py
示例8: test_no_gmail_quote_false_positive
def test_no_gmail_quote_false_positive():
msg_body = """
<html><body>
<div class="gmail_quote">
broken_email_client_sent_this
</div>
</body></html>"""
eq_("<html><body><div>broken_email_client_sent_this</div></body></html>",
RE_WHITESPACE.sub('', quotations.extract_from_html(msg_body)))
开发者ID:JordanReiter，项目名称:talon，代码行数:9，代码来源:html_quotations_test.py
示例9: test_gmail_quote_blockquote
def test_gmail_quote_blockquote():
msg_body = """Message
<blockquote class="gmail_quote">
<div class="gmail_default">
My name is William Shakespeare.
<br/>
</div>
</blockquote>"""
eq_(RE_WHITESPACE.sub('', msg_body),
RE_WHITESPACE.sub('', quotations.extract_from_html(msg_body)))
开发者ID:guruhq，项目名称:talon，代码行数:10，代码来源:html_quotations_test.py
示例10: test_CRLF
def test_CRLF():
"""CR is not converted to ' '
"""
eq_('<html>\r\n</html>', quotations.extract_from_html('<html>\r\n</html>'))
msg_body = """Reply
<blockquote>
<div>
On 11-Apr-2011, at 6:54 PM, Bob <[email protected]> wrote:
</div>
<div>
Test
</div>
</blockquote>"""
msg_body = msg_body.replace('\n', '\r\n')
eq_("<html><body><p>Reply\r\n</p></body></html>",
quotations.extract_from_html(msg_body))
开发者ID:clara-labs，项目名称:talon，代码行数:20，代码来源:html_quotations_test.py
示例11: test_gmail_quote
def test_gmail_quote():
msg_body = """Reply
<div class="gmail_quote">
<div class="gmail_quote">
On 11-Apr-2011, at 6:54 PM, Bob <[email protected]> wrote:
<div>
Test
</div>
</div>
</div>"""
eq_("<html><body><p>Reply</p></body></html>",
RE_WHITESPACE.sub('', quotations.extract_from_html(msg_body)))
开发者ID:clara-labs，项目名称:talon，代码行数:12，代码来源:html_quotations_test.py
示例12: extract_body
def extract_body(message: message.Message) -> Text:
# If the message contains a plaintext version of the body, use
# that.
plaintext_content = get_message_part_by_type(message, "text/plain")
if plaintext_content:
return quotations.extract_from_plain(plaintext_content)
# If we only have an HTML version, try to make that look nice.
html_content = get_message_part_by_type(message, "text/html")
if html_content:
return convert_html_to_markdown(quotations.extract_from_html(html_content))
raise ZulipEmailForwardError("Unable to find plaintext or HTML message body")
开发者ID:joydeep1701，项目名称:zulip，代码行数:13，代码来源:email_mirror.py
示例13: test_unicode_in_reply
def test_unicode_in_reply():
msg_body = u"""Reply \xa0 \xa0 Text<br>
<div>
<br>
</div>
<blockquote>
Quote
</blockquote>""".encode("utf-8")
eq_("<html><head></head><body>Reply  Text<br><div><br></div>"
"</body></html>",
RE_WHITESPACE.sub('', quotations.extract_from_html(msg_body)))
开发者ID:guruhq，项目名称:talon，代码行数:14，代码来源:html_quotations_test.py
示例14: test_from_block
def test_from_block():
msg_body = """<div>
message<br>
<div>
<hr>
From: <a href="mailto:[email protected]">[email protected]</a><br>
Date: Fri, 23 Mar 2012 12:35:31 -0600<br>
To: <a href="mailto:[email protected]">[email protected]</a><br>
Subject: You Have New Mail From Mary!<br><br>
text
</div></div>
"""
eq_('<html><head></head><body><div>message<br></div></body></html>',
RE_WHITESPACE.sub('', quotations.extract_from_html(msg_body)))
开发者ID:guruhq，项目名称:talon，代码行数:15，代码来源:html_quotations_test.py
示例15: test_quotation_splitter_outside_blockquote
def test_quotation_splitter_outside_blockquote():
msg_body = """Reply
<div>
On 11-Apr-2011, at 6:54 PM, Bob <[email protected]> wrote:
</div>
<blockquote>
<div>
Test
</div>
</blockquote>
"""
eq_("<html><head></head><body>Reply</body></html>",
RE_WHITESPACE.sub('', quotations.extract_from_html(msg_body)))
开发者ID:guruhq，项目名称:talon，代码行数:15，代码来源:html_quotations_test.py
示例16: extract_reply_and_check
def extract_reply_and_check(filename):
import sys
kwargs = {}
if sys.version_info > (3, 0):
kwargs["encoding"] = "utf8"
f = open(filename, **kwargs)
msg_body = f.read()
reply = quotations.extract_from_html(msg_body)
plain_reply = u.html_to_text(reply)
plain_reply = plain_reply.decode('utf8')
eq_(RE_WHITESPACE.sub('', "Hi. I am fine.\n\nThanks,\nAlex"),
RE_WHITESPACE.sub('', plain_reply))
开发者ID:guruhq，项目名称:talon，代码行数:15，代码来源:html_quotations_test.py
示例17: test_regular_blockquote
def test_regular_blockquote():
msg_body = """Reply
<blockquote>Regular</blockquote>
<div>
On 11-Apr-2011, at 6:54 PM, Bob <[email protected]> wrote:
</div>
<blockquote>
<div>
<blockquote>Nested</blockquote>
</div>
</blockquote>
"""
eq_("<html><head></head><body>Reply<blockquote>Regular</blockquote></body></html>",
RE_WHITESPACE.sub('', quotations.extract_from_html(msg_body)))
开发者ID:guruhq，项目名称:talon，代码行数:16，代码来源:html_quotations_test.py
示例18: test_readable_html_empty
def test_readable_html_empty():
msg_body = """
<blockquote>
Reply
<div>
On 11-Apr-2011, at 6:54 PM, Bob <[email protected]> wrote:
</div>
<div>
Test
</div>
</blockquote>"""
eq_(RE_WHITESPACE.sub('', msg_body),
RE_WHITESPACE.sub('', quotations.extract_from_html(msg_body)))
开发者ID:guruhq，项目名称:talon，代码行数:16，代码来源:html_quotations_test.py
示例19: test_quotation_splitter_inside_blockquote
def test_quotation_splitter_inside_blockquote():
msg_body = """Reply
<blockquote>
<div>
On 11-Apr-2011, at 6:54 PM, Bob <[email protected]> wrote:
</div>
<div>
Test
</div>
</blockquote>"""
eq_("<html><body><p>Reply\n</p></body></html>",
quotations.extract_from_html(msg_body))
开发者ID:clara-labs，项目名称:talon，代码行数:16，代码来源:html_quotations_test.py
示例20: test_reply_shares_div_with_from_block
def test_reply_shares_div_with_from_block():
msg_body = '''
<body>
<div>
Blah<br><br>
<hr>Date: Tue, 22 May 2012 18:29:16 -0600<br>
To: [email protected]<br>
From: [email protected]<br>
Subject: You Have New Mail From x!<br><br>
</div>
</body>'''
eq_('<html><head></head><body><div>Blah<br><br></div></body></html>',
RE_WHITESPACE.sub('', quotations.extract_from_html(msg_body)))
开发者ID:guruhq，项目名称:talon，代码行数:16，代码来源:html_quotations_test.py
注：本文中的talon.quotations.extract_from_html函数示例由纯净天空整理自Github/MSDocs等源码及文档管理平台，相关代码片段筛选自各路编程大神贡献的开源项目，源码版权归原作者所有，传播和使用请参考对应项目的License；未经允许，请勿转载。 |
客服电话
APP下载
官方微信
请发表评论