kb.pageEncoding = None else: kb.pageEncoding = conf.charset # can't do for all responses because we need to support binary files too if contentType and not isinstance(page, unicode) and "text/" in contentType.lower(): # e.g. Ãëàâà if "&#" in page: page = re.sub(r"&#(\d{1,3});", lambda _: chr(int(_.group(1))) if int(_.group(1)) < 256 else _.group(0), page) # e.g. %20%28%29 if "%" in page: page = re.sub(r"%([0-9a-fA-F]{2})", lambda _: _.group(1).decode("hex"), page) # e.g. & page = re.sub(r"&([^;]+);", lambda _: chr(htmlEntities[_.group(1)]) if htmlEntities.get(_.group(1), 256) < 256 else _.group(0), page) kb.pageEncoding = kb.pageEncoding or checkCharEncoding(getHeuristicCharEncoding(page)) page = getUnicode(page, kb.pageEncoding) # e.g. ’…™ if "&#" in page: page = re.sub(r"&#(\d+);", lambda _: unichr(int(_.group(1))), page) # e.g. ζ page = re.sub(r"&([^;]+);", lambda _: unichr(htmlEntities[_.group(1)]) if htmlEntities.get(_.group(1), 0) > 255 else _.group(0), page) return page def processResponse(page, responseHeaders): kb.processResponseCounter += 1
kb.pageEncoding = conf.charset # can't do for all responses because we need to support binary files too if contentType and not isinstance(page, unicode) and any( map(lambda x: x in contentType.lower(), ("text/txt", "text/raw", "text/html", "text/xml"))): # e.g. Ãëàâà if "&#" in page: page = re.sub( '&#(\d{1,3});', lambda _: chr(int(_.group(1))) if int(_.group(1)) < 256 else _.group(0), page) # e.g. & page = re.sub( '&([^;]+);', lambda _: chr(htmlEntities[_.group(1)]) if htmlEntities.get(_.group(1), 256) < 256 else _.group(0), page) kb.pageEncoding = kb.pageEncoding or checkCharEncoding( getHeuristicCharEncoding(page)) page = getUnicode(page, kb.pageEncoding) # e.g. ’…™ if "&#" in page: page = re.sub('&#(\d+);', lambda _: unichr(int(_.group(1))), page) # e.g. ζ page = re.sub( '&([^;]+);', lambda _: unichr(htmlEntities[_.group(1)]) if htmlEntities.get(_.group(1), 0) > 255 else _.group(0), page) return page
if ((httpCharset or metaCharset) and not all([httpCharset, metaCharset]))\ or (httpCharset == metaCharset and all([httpCharset, metaCharset])): kb.pageEncoding = httpCharset or metaCharset else: kb.pageEncoding = None else: kb.pageEncoding = conf.charset # can't do for all responses because we need to support binary files too if contentType and not isinstance(page, unicode) and any(map(lambda _: _ in contentType.lower(), ("text/txt", "text/raw", "text/html", "text/xml"))): # e.g. Ãëàâà if "&#" in page: page = re.sub('&#(\d{1,3});', lambda _: chr(int(_.group(1))) if int(_.group(1)) < 256 else _.group(0), page) # e.g. & page = re.sub('&([^;]+);', lambda _: chr(htmlEntities[_.group(1)]) if htmlEntities.get(_.group(1), 256) < 256 else _.group(0), page) kb.pageEncoding = kb.pageEncoding or checkCharEncoding(getHeuristicCharEncoding(page)) page = getUnicode(page, kb.pageEncoding) # e.g. ’…™ if "&#" in page: page = re.sub('&#(\d+);', lambda _: unichr(int(_.group(1))), page) # e.g. ζ page = re.sub('&([^;]+);', lambda _: unichr(htmlEntities[_.group(1)]) if htmlEntities.get(_.group(1), 0) > 255 else _.group(0), page) return page def processResponse(page, responseHeaders): kb.processResponseCounter += 1