github/plexpy
1
0
Fork 0
mirror of https://github.com/Tautulli/Tautulli.git synced 2025-08-14 02:26:58 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

Update bs4 to 4.8.1 (with 2to3)

Browse source
This commit is contained in:
JonnyWong16 2019-11-23 18:54:24 -08:00
commit f28e741ad7
19 changed files with 5487 additions and 792 deletions
Download patch file Download diff file Expand all files Collapse all files

88
lib/bs4/diagnose.py
View file

@ -1,7 +1,11 @@
"""Diagnostic functions, mainly for use when doing tech support."""
# Use of this source code is governed by the MIT license.
__license__ = "MIT"
import cProfile
from StringIO import StringIO
from HTMLParser import HTMLParser
from io import StringIO
from html.parser import HTMLParser
import bs4
from bs4 import BeautifulSoup, __version__
from bs4.builder import builder_registry
@ -17,8 +21,8 @@ import cProfile
def diagnose(data):
"""Diagnostic suite for isolating common problems."""
print "Diagnostic running on Beautiful Soup %s" % __version__
print "Python version %s" % sys.version
print("Diagnostic running on Beautiful Soup %s" % __version__)
print("Python version %s" % sys.version)
basic_parsers = ["html.parser", "html5lib", "lxml"]
for name in basic_parsers:
@ -27,44 +31,60 @@ def diagnose(data):
break
else:
basic_parsers.remove(name)
print (
print((
"I noticed that %s is not installed. Installing it may help." %
name)
name))
if 'lxml' in basic_parsers:
basic_parsers.append(["lxml", "xml"])
from lxml import etree
print "Found lxml version %s" % ".".join(map(str,etree.LXML_VERSION))
basic_parsers.append("lxml-xml")
try:
from lxml import etree
print("Found lxml version %s" % ".".join(map(str,etree.LXML_VERSION)))
except ImportError as e:
print (
"lxml is not installed or couldn't be imported.")
if 'html5lib' in basic_parsers:
import html5lib
print "Found html5lib version %s" % html5lib.__version__
try:
import html5lib
print("Found html5lib version %s" % html5lib.__version__)
except ImportError as e:
print (
"html5lib is not installed or couldn't be imported.")
if hasattr(data, 'read'):
data = data.read()
elif os.path.exists(data):
print '"%s" looks like a filename. Reading data from the file.' % data
data = open(data).read()
elif data.startswith("http:") or data.startswith("https:"):
print '"%s" looks like a URL. Beautiful Soup is not an HTTP client.' % data
print "You need to use some other library to get the document behind the URL, and feed that document to Beautiful Soup."
print('"%s" looks like a URL. Beautiful Soup is not an HTTP client.' % data)
print("You need to use some other library to get the document behind the URL, and feed that document to Beautiful Soup.")
return
print
else:
try:
if os.path.exists(data):
print('"%s" looks like a filename. Reading data from the file.' % data)
with open(data) as fp:
data = fp.read()
except ValueError:
# This can happen on some platforms when the 'filename' is
# too long. Assume it's data and not a filename.
pass
print()
for parser in basic_parsers:
print "Trying to parse your markup with %s" % parser
print("Trying to parse your markup with %s" % parser)
success = False
try:
soup = BeautifulSoup(data, parser)
soup = BeautifulSoup(data, features=parser)
success = True
except Exception, e:
print "%s could not parse the markup." % parser
except Exception as e:
print("%s could not parse the markup." % parser)
traceback.print_exc()
if success:
print "Here's what %s did with the markup:" % parser
print soup.prettify()
print("Here's what %s did with the markup:" % parser)
print(soup.prettify())
print "-" * 80
print("-" * 80)
def lxml_trace(data, html=True, **kwargs):
"""Print out the lxml events that occur during parsing.
@ -74,7 +94,7 @@ def lxml_trace(data, html=True, **kwargs):
"""
from lxml import etree
for event, element in etree.iterparse(StringIO(data), html=html, **kwargs):
print("%s, %4s, %s" % (event, element.tag, element.text))
print(("%s, %4s, %s" % (event, element.tag, element.text)))
class AnnouncingParser(HTMLParser):
"""Announces HTMLParser parse events, without doing anything else."""
@ -135,7 +155,7 @@ def rword(length=5):
def rsentence(length=4):
"Generate a random sentence-like string."
return " ".join(rword(random.randint(4,9)) for i in range(length))
def rdoc(num_elements=1000):
"""Randomly generate an invalid HTML document."""
tag_names = ['p', 'div', 'span', 'i', 'b', 'script', 'table']
@ -156,10 +176,10 @@ def rdoc(num_elements=1000):
def benchmark_parsers(num_elements=100000):
"""Very basic head-to-head performance benchmark."""
print "Comparative parser benchmark on Beautiful Soup %s" % __version__
print("Comparative parser benchmark on Beautiful Soup %s" % __version__)
data = rdoc(num_elements)
print "Generated a large invalid HTML document (%d bytes)." % len(data)
print("Generated a large invalid HTML document (%d bytes)." % len(data))
for parser in ["lxml", ["lxml", "html"], "html5lib", "html.parser"]:
success = False
try:
@ -167,24 +187,24 @@ def benchmark_parsers(num_elements=100000):
soup = BeautifulSoup(data, parser)
b = time.time()
success = True
except Exception, e:
print "%s could not parse the markup." % parser
except Exception as e:
print("%s could not parse the markup." % parser)
traceback.print_exc()
if success:
print "BS4+%s parsed the markup in %.2fs." % (parser, b-a)
print("BS4+%s parsed the markup in %.2fs." % (parser, b-a))
from lxml import etree
a = time.time()
etree.HTML(data)
b = time.time()
print "Raw lxml parsed the markup in %.2fs." % (b-a)
print("Raw lxml parsed the markup in %.2fs." % (b-a))
import html5lib
parser = html5lib.HTMLParser()
a = time.time()
parser.parse(data)
b = time.time()
print "Raw html5lib parsed the markup in %.2fs." % (b-a)
print("Raw html5lib parsed the markup in %.2fs." % (b-a))
def profile(num_elements=100000, parser="lxml"):