aee018f39c813bb3ff12f67f19022d5c584f629b,vendor/readability/encoding.py,,get_encoding,#Any#,4

Before Change

def get_encoding(page):
    // Regex for XML and HTML Meta charset declaration
    charset_re = re.compile(r"<meta.*?charset=["\"]*(.+?)["\">]", flags=re.I)
    pragma_re = re.compile(r"<meta.*?content=["\"]*;?charset=(.+?)["\">]", flags=re.I)
    xml_re = re.compile(r"^<\?xml.*?encoding=["\"]*(.+?)["\">]")

    declared_encodings = (charset_re.findall(page) +
            pragma_re.findall(page) +

After Change

            // Now let"s decode the page
            page.decode()
            // It worked!
            return encoding
        except UnicodeDecodeError:
            pass

    // Fallback to chardet if declared encodings fail

Instances