diff options
Diffstat (limited to 'bs4/diagnose.py')
| -rw-r--r-- | bs4/diagnose.py | 52 |
1 files changed, 26 insertions, 26 deletions
diff --git a/bs4/diagnose.py b/bs4/diagnose.py index e4f2f47..500e92d 100644 --- a/bs4/diagnose.py +++ b/bs4/diagnose.py @@ -4,8 +4,8 @@ __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 @@ -25,8 +25,8 @@ def diagnose(data): :param data: A string containing markup that needs to be explained. :return: None; diagnostics are printed to standard output. """ - 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: @@ -35,16 +35,16 @@ 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") try: from lxml import etree - print("Found lxml version %s" % ".".join(map(str,etree.LXML_VERSION))) - except ImportError, e: + 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.") @@ -52,21 +52,21 @@ def diagnose(data): if 'html5lib' in basic_parsers: try: import html5lib - print("Found html5lib version %s" % html5lib.__version__) - except ImportError, e: + 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 data.startswith("http:") or data.startswith("https:"): - print('"%s" looks like a URL. Beautiful Soup is not an HTTP client.' % data) + 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 else: try: if os.path.exists(data): - print('"%s" looks like a filename. Reading data from the file.' % data) + print(('"%s" looks like a filename. Reading data from the file.' % data)) with open(data) as fp: data = fp.read() except ValueError: @@ -76,19 +76,19 @@ def diagnose(data): 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, 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. @@ -104,7 +104,7 @@ 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): """Subclass of HTMLParser that announces parse events, without doing @@ -193,9 +193,9 @@ 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 @@ -204,24 +204,24 @@ 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"): """Use Python's profiler on a randomly generated document.""" |