| Server IP : 127.0.0.2 / Your IP : 18.117.9.230 Web Server : Apache/2.4.18 (Ubuntu) System : User : www-data ( ) PHP Version : 7.0.33-0ubuntu0.16.04.16 Disable Function : disk_free_space,disk_total_space,diskfreespace,dl,exec,fpaththru,getmyuid,getmypid,highlight_file,ignore_user_abord,leak,listen,link,opcache_get_configuration,opcache_get_status,passthru,pcntl_alarm,pcntl_fork,pcntl_waitpid,pcntl_wait,pcntl_wifexited,pcntl_wifstopped,pcntl_wifsignaled,pcntl_wexitstatus,pcntl_wtermsig,pcntl_wstopsig,pcntl_signal,pcntl_signal_dispatch,pcntl_get_last_error,pcntl_strerror,pcntl_sigprocmask,pcntl_sigwaitinfo,pcntl_sigtimedwait,pcntl_exec,pcntl_getpriority,pcntl_setpriority,php_uname,phpinfo,posix_ctermid,posix_getcwd,posix_getegid,posix_geteuid,posix_getgid,posix_getgrgid,posix_getgrnam,posix_getgroups,posix_getlogin,posix_getpgid,posix_getpgrp,posix_getpid,posix,_getppid,posix_getpwnam,posix_getpwuid,posix_getrlimit,posix_getsid,posix_getuid,posix_isatty,posix_kill,posix_mkfifo,posix_setegid,posix_seteuid,posix_setgid,posix_setpgid,posix_setsid,posix_setuid,posix_times,posix_ttyname,posix_uname,pclose,popen,proc_open,proc_close,proc_get_status,proc_nice,proc_terminate,shell_exec,source,show_source,system,virtual MySQL : OFF | cURL : ON | WGET : ON | Perl : ON | Python : ON | Sudo : ON | Pkexec : ON Directory : /usr/lib/python2.7/dist-packages/bs4/tests/ |
Upload File : |
"""Tests to ensure that the html5lib tree builder generates good trees."""
import warnings
try:
from bs4.builder import HTML5TreeBuilder
HTML5LIB_PRESENT = True
except ImportError, e:
HTML5LIB_PRESENT = False
from bs4.element import SoupStrainer
from bs4.testing import (
HTML5TreeBuilderSmokeTest,
SoupTest,
skipIf,
)
@skipIf(
not HTML5LIB_PRESENT,
"html5lib seems not to be present, not testing its tree builder.")
class HTML5LibBuilderSmokeTest(SoupTest, HTML5TreeBuilderSmokeTest):
"""See ``HTML5TreeBuilderSmokeTest``."""
@property
def default_builder(self):
return HTML5TreeBuilder()
def test_soupstrainer(self):
# The html5lib tree builder does not support SoupStrainers.
strainer = SoupStrainer("b")
markup = "<p>A <b>bold</b> statement.</p>"
with warnings.catch_warnings(record=True) as w:
soup = self.soup(markup, parse_only=strainer)
self.assertEqual(
soup.decode(), self.document_for(markup))
self.assertTrue(
"the html5lib tree builder doesn't support parse_only" in
str(w[0].message))
def test_correctly_nested_tables(self):
"""html5lib inserts <tbody> tags where other parsers don't."""
markup = ('<table id="1">'
'<tr>'
"<td>Here's another table:"
'<table id="2">'
'<tr><td>foo</td></tr>'
'</table></td>')
self.assertSoupEquals(
markup,
'<table id="1"><tbody><tr><td>Here\'s another table:'
'<table id="2"><tbody><tr><td>foo</td></tr></tbody></table>'
'</td></tr></tbody></table>')
self.assertSoupEquals(
"<table><thead><tr><td>Foo</td></tr></thead>"
"<tbody><tr><td>Bar</td></tr></tbody>"
"<tfoot><tr><td>Baz</td></tr></tfoot></table>")
def test_xml_declaration_followed_by_doctype(self):
markup = '''<?xml version="1.0" encoding="utf-8"?>
<!DOCTYPE html>
<html>
<head>
</head>
<body>
<p>foo</p>
</body>
</html>'''
soup = self.soup(markup)
# Verify that we can reach the <p> tag; this means the tree is connected.
self.assertEqual(b"<p>foo</p>", soup.p.encode())
def test_reparented_markup(self):
markup = '<p><em>foo</p>\n<p>bar<a></a></em></p>'
soup = self.soup(markup)
self.assertEqual(u"<body><p><em>foo</em></p><em>\n</em><p><em>bar<a></a></em></p></body>", soup.body.decode())
self.assertEqual(2, len(soup.find_all('p')))
def test_reparented_markup_ends_with_whitespace(self):
markup = '<p><em>foo</p>\n<p>bar<a></a></em></p>\n'
soup = self.soup(markup)
self.assertEqual(u"<body><p><em>foo</em></p><em>\n</em><p><em>bar<a></a></em></p>\n</body>", soup.body.decode())
self.assertEqual(2, len(soup.find_all('p')))
def test_processing_instruction(self):
"""Processing instructions become comments."""
markup = b"""<?PITarget PIContent?>"""
soup = self.soup(markup)
assert str(soup).startswith("<!--?PITarget PIContent?-->")
def test_cloned_multivalue_node(self):
markup = b"""<a class="my_class"><p></a>"""
soup = self.soup(markup)
a1, a2 = soup.find_all('a')
self.assertEqual(a1, a2)
assert a1 is not a2