관리-도구
편집 파일: clean.cpython-37.pyc
B o��] i � @ s� d Z ddlmZ ddlZddlZy ddlmZ ddlmZ W n$ e k r` ddl mZmZ Y nX ddl m Z ddl mZ dd l mZmZ dd l mZmZ ye W n ek r� eZY nX ye W n ek r� eZY nX ye W n ek �r eefZY nX d d d ddddgZe�dej ej B �Z e�dej �Z e�dej �j Z!e�dej �j Z"dd� Z#e�d�j$Z%e�dej ej B �Z&e �'d�Z(e j'dd eid �Z)G d d � d e*�Z+e+� Z,e,j-Z-e�d ej �e�d ej �gZ.d!d"d#d$d%d&gZ/e�d'ej �e�d(ej �e�d)�gZ0d*gZ1e.e/e0e1fd+d�Z2d,d-� Z3d.d� Z4e2j e4_ d"d!d#gZ5d/gZ6d0e5e6ed1�fd2d�Z7d3d� Z8d4d5� Z9e�d6ej �Z:d7d8� Z;dS )9zcA cleanup tool for HTML. Removes unwanted tags and content. See the `Cleaner` class for details. � )�absolute_importN)�urlsplit)� unquote_plus)r r )�etree)�defs)� fromstring�XHTML_NAMESPACE)� xhtml_to_html�_transform_result� clean_html�clean�Cleaner�autolink� autolink_html� word_break�word_break_htmlzexpression\s*\(.*?\)z @\s*importz^data:image/.+;base64z<(?:javascript|jscript|livescript|vbscript|data|about|mocha):c C s t | �r d S t| �S )N)�_is_image_dataurl� _is_possibly_malicious_scheme)�s� r �B/opt/alt/python37/lib64/python3.7/site-packages/lxml/html/clean.py�_is_javascript_schemeN s r z [\s\x00-\x08\x0B\x0C\x0E-\x19]+z\[if[\s\n\r]+.*?][\s\n\r]*>z descendant-or-self::*[@style]z�descendant-or-self::a [normalize-space(@href) and substring(normalize-space(@href),1,1) != '#'] |descendant-or-self::x:a[normalize-space(@href) and substring(normalize-space(@href),1,1) != '#']�x)Z namespacesc @ s� e Zd ZdZdZdZdZdZdZdZ dZ dZ dZ dZ dZdZdZdZdZdZdZdZejZdZdZddhZdd � Ze d d d d gd d d d d�Z dd� Z dd� Z dd� Z dd� Z!dd� Z"d"dd�Z#dd � Z$e%�&d e%j'�j(Z)d d � Z*d d!� Z+dS )#r a Instances cleans the document of each of the possible offending elements. The cleaning is controlled by attributes; you can override attributes in a subclass, or set them in the constructor. ``scripts``: Removes any ``<script>`` tags. ``javascript``: Removes any Javascript, like an ``onclick`` attribute. Also removes stylesheets as they could contain Javascript. ``comments``: Removes any comments. ``style``: Removes any style tags. ``inline_style`` Removes any style attributes. Defaults to the value of the ``style`` option. ``links``: Removes any ``<link>`` tags ``meta``: Removes any ``<meta>`` tags ``page_structure``: Structural parts of a page: ``<head>``, ``<html>``, ``<title>``. ``processing_instructions``: Removes any processing instructions. ``embedded``: Removes any embedded objects (flash, iframes) ``frames``: Removes any frame-related tags ``forms``: Removes any form tags ``annoying_tags``: Tags that aren't *wrong*, but are annoying. ``<blink>`` and ``<marquee>`` ``remove_tags``: A list of tags to remove. Only the tags will be removed, their content will get pulled up into the parent tag. ``kill_tags``: A list of tags to kill. Killing also removes the tag's content, i.e. the whole subtree, not just the tag itself. ``allow_tags``: A list of tags to include (default include all). ``remove_unknown_tags``: Remove any tags that aren't standard parts of HTML. ``safe_attrs_only``: If true, only include 'safe' attributes (specifically the list from the feedparser HTML sanitisation web site). ``safe_attrs``: A set of attribute names to override the default list of attributes considered 'safe' (when safe_attrs_only=True). ``add_nofollow``: If true, then any <a> tags will have ``rel="nofollow"`` added to them. ``host_whitelist``: A list or set of hosts that you can use for embedded content (for content like ``<object>``, ``<link rel="stylesheet">``, etc). You can also implement/override the method ``allow_embedded_url(el, url)`` or ``allow_element(el)`` to implement more complex rules for what can be embedded. Anything that passes this test will be shown, regardless of the value of (for instance) ``embedded``. Note that this parameter might not work as intended if you do not make the links absolute before doing the cleaning. Note that you may also need to set ``whitelist_tags``. ``whitelist_tags``: A set of tags that can be included with ``host_whitelist``. The default is ``iframe`` and ``embed``; you may wish to include other tags like ``script``, or you may want to implement ``allow_embedded_url`` for more control. Set to None to include all tags. This modifies the document *in place*. TFNr �iframe�embedc K sZ x:|� � D ].\}}t| |�s,td||f ��t| ||� q W | jd krVd|krV| j| _d S )NzUnknown parameter: %s=%r� inline_style)�items�hasattr� TypeError�setattrr �style)�self�kw�name�valuer r r �__init__� s zCleaner.__init__�src�href�code�object)�script�link�appletr r �layer�ac C s� t |d�r|�� }t|� x|�d�D ] }d|_q&W | jsD| �|� t| jpNd�}t| j p\d�}t| j pjd�}| j r~|� d� | j r�t| j�}x:|�tj�D ]*}|j}x |�� D ]}||kr�||= q�W q�W | j�r2| j r�| jtjk�s(x@|�tj�D ]0}|j}x$|�� D ]}|�d��r||= �qW q�W |j| jdd� | j�s�x`t|�D ]T}|�d �} t� d | �} t � d | �} | � | ��r�|jd = n| | k�rJ|�d | � �qJW | j �s2x�t |�d ��D ]t}|�d d ��!� �"� d k�r�|�#� �q�|j$�p�d } t� d | �} t � d | �} | � | ��r d |_$n| | k�r�| |_$�q�W | j�sB| j%�rN|� tj&� | j%�rb|� tj'� | j �rt|� d � | j�r�t�(|d � | j)�r�|� d� nT| j �s�| j�r�xBt |�d��D ]0}d|�dd ��!� k�r�| �*|��s�|�#� �q�W | j+�r|� d� | j,�r|�-d� | j.�r�x\t |�d��D ]J}d} |�/� } x$| dk �r`| jdk�r`| �/� } �q>W | dk�r,|�#� �q,W |�-d� |�-d� | j0�r�|�-tj1� | j2�r�|� d� |�-d� | j3�r�|�-d� g } g }x`|�� D ]T}|j|k�r| �*|��r�q�|�4|� n&|j|k�r�| �*|��r*�q�| �4|� �q�W | �rj| d |k�rj| �5d�}d |_|j�6� n8|�r�|d |k�r�|�5d�}|jd k�r�d |_|�6� |�7� x|D ]}|�#� �q�W x| D ]}|�8� �q�W | j9�r�|�r�t:d ��ttj;�}|�rtg }x(|�� D ] }|j|k�r|�4|� �qW |�rt|d |k�r\|�5d�}d |_|j�6� x|D ]}|�8� �qbW | j<�r�xdt=|�D ]X}| �>|��s�|�d�}|�r�d |k�r�d d!| k�rq�d"| }nd }|�d|� �q�W dS )#z& Cleans the document. �getrootZimageZimgr r* �onF)Zresolve_base_hrefr � �typeztext/javascriptz /* deleted */r+ Z stylesheet�rel�meta)�head�html�title�paramN)r, r) )r, )r r r- r) r8 Zform)Zbutton�input�select�textarea)ZblinkZmarqueer Zdivr6 zIIt does not make sense to pass in both allow_tags and remove_unknown_tagsZnofollowz nofollow z %s z %s nofollow)?r r/ r �iter�tag�comments�kill_conditional_comments�set� kill_tags� remove_tags� allow_tags�scripts�add�safe_attrs_only� safe_attrsr ZElement�attrib�keys� javascriptr � startswithZ rewrite_links�_remove_javascript_linkr �_find_styled_elements�get�_css_javascript_re�sub�_css_import_re�_has_sneaky_javascriptr �list�lower�strip� drop_tree�text�processing_instructions�CommentZProcessingInstructionZstrip_attributes�links� allow_elementr4 �page_structure�update�embeddedZ getparent�framesZ frame_tags�forms� annoying_tags�append�pop�clear�reverseZdrop_tag�remove_unknown_tags� ValueErrorZtags� add_nofollow�_find_external_links� allow_follow)r! �doc�elrA rB rC rG rH �aname�old�newZ found_parent�parent�_removeZ_kill�badr3 r r r �__call__� s zCleaner.__call__c C s dS )zF Override to suppress rel="nofollow" on some anchors. Fr )r! �anchorr r r rj � s zCleaner.allow_followc C s� |j | jkrdS | j|j }t|ttf�r^x.|D ]&}|�|�}|sFdS | �||�s0dS q0W dS |�|�}|spdS | �||�S dS )z� Decide whether an element is configured to be accepted or rejected. :param el: an element. :return: true to accept the element or false to reject/discard it. FTN)r= �_tag_link_attrs� isinstancerS �tuplerN �allow_embedded_url)r! rl �attrZone_attr�urlr r r r[ � s zCleaner.allow_elementc C s^ | j dk r|j| j krdS t|�\}}}}}|�� �dd�d }|dkrLdS || jkrZdS dS )a Decide whether a URL that was found in an element's attributes or text if configured to be accepted or rejected. :param el: an element. :param url: a URL found on the element. :return: true to accept the URL and false to reject it. NF�:� r )�http�httpsT)�whitelist_tagsr= r rT �split�host_whitelist)r! rl rz �scheme�netloc�path�query�fragmentr r r rx � s zCleaner.allow_embedded_urlc C s g }| � |dd� tj� dS )z� IE conditional comments basically embed HTML that the parser doesn't normally see. We can't allow anything like that, so we'll kill any comments that could be conditional. c S s t �| j�S )N)�_conditional_comment_re�searchrW )rl r r r �<lambda>� � z3Cleaner.kill_conditional_comments.<locals>.<lambda>N)�_kill_elementsr rY )r! rk rr r r r r? � s z!Cleaner.kill_conditional_commentsc C sD g }x$|� |�D ]}||�r|�|� qW x|D ] }|�� q0W d S )N)r< rb rV )r! rk Z condition�iteraterr rl r r r r� � s zCleaner._kill_elementsc C s t dt|��}t|�rdS |S )Nr1 )�_substitute_whitespacer r )r! r+ ro r r r rL � s z Cleaner._remove_javascript_linkz /\*.*?\*/c C sF | � d|�}|�dd�}td|�}|�� }d|kr6dS d|krBdS dS )a� Depending on the browser, stuff like ``e x p r e s s i o n(...)`` can get interpreted, or ``expre/* stuff */ssion(...)``. This checks for attempt to do stuff like this. Typically the response will be to kill the entire style; if you have just a bit of Javascript in the style another rule will catch that and remove only the Javascript from the style; this catches more sneaky attempts. r1 �\z javascript:Tz expression(F)�_substitute_comments�replacer� rT )r! r r r r rR � s z Cleaner._has_sneaky_javascriptc C s8 t |�}t|t�r t|�}n t�|�}| |� t||�S )N)r2 rv � basestringr �copy�deepcopyr )r! r6 � result_typerk r r r r s zCleaner.clean_html)N),�__name__� __module__� __qualname__�__doc__rD rJ r> r r rZ r4 r\ rX r^ r_ r` ra rB rC rA rf rF r rG rh r� r r% �dictru rs rj r[ rx r? r� rL �re�compile�SrP r� rR r r r r r r c sV ] 5 zb(?P<body>https?://(?P<host>[a-z0-9._-]+)(?:/[/\-_.,a-z0-9%&?;=~]*)?(?:\([/\-_.,a-z0-9%&?;=~]*\))?)z9mailto:(?P<body>[a-z0-9._-]+@(?P<host>[a-z0-9_.-]+[a-z]))r; �prer( r5 r: r. z ^localhostz\bexample\.(?:com|org|net)$z^127\.0\.0\.1$Znolinkc C s� | j |krdS | �d�}|r>|�� }x|D ]}||kr*dS q*W xht| �D ]\}t|||||d� |jrHt|j||| jd�\}} | rH||_| �|�} | | | d | d �< qHW | j r�t| j ||| jd�\}} | r�|| _ | | dd�< dS )a Turn any URLs into links. It will search for links identified by the given regular expressions (by default mailto and http(s) links). It won't link text in an element in avoid_elements, or an element with a class in avoid_classes. It won't link to anything with a host that matches one of the regular expressions in avoid_hosts (default localhost and 127.0.0.1). If you pass in an element, the element's tail will not be substituted, only the contents of the element. N�class)� link_regexes�avoid_elements� avoid_hosts� avoid_classes)�factoryr| r ) r= rN r� rS r �tail� _link_textZ makeelement�indexrW ) rl r� r� r� r� � class_nameZ match_class�childrW Z tail_childrenr� Z pre_childrenr r r r / s4 c C s� d}g }d}�x�d\}}x�|D ]~} |} xJ| j | | d�} | d kr@P | �d�} x"|D ]} | � | �rP| �� } P qPW P q(W | d kr|q |d ks�| �� |k r | }| �� }q W |d kr�|r�|d jr�t�| |d _n |r�t�| }P |�d�}|�� }|�d�s�|�d��r|d 8 }|d d� }| d |�� � }|�rB|d j�r6t�||d _n|�rLt�|}|d �}|�d |� |�d �}|�sx|}|�d��s�|�d��r�|d d� }||_|� |� | |d � } qW ||fS ) Nr1 r )NN)�pos�host����.�,r| r. r' �body) r� �group�end�startr� �AssertionError�endswithr@ rW rb )rW r� r� r� Z leading_textrZ Zlast_pos� best_matchZbest_posZregexZ regex_pos�matchr� Z host_regexr+ r� Z prev_textrt r� r r r r� \ sf r� c O s@ t | �}t| t�r t| �}n t�| �}t|f|�|� t||�S )N)r2 rv r� r r� r� r r )r6 �argsr" r� rk r r r r � s Znobreak�( i c C s� | j tkrdS | �d�}|rLd}|�� }x|D ]}||kr.d}P q.W |rLdS | jrbt| j||�| _x4| D ],}t|||||d� |jrht|j||�|_qhW dS )a� Breaks any long words found in the body of the text (not attributes). Doesn't effect any of the tags in avoid_elements, by default ``<textarea>`` and ``<pre>`` Breaks words by inserting ​, which is a unicode character for Zero Width Space character. This generally takes up no space in rendering, but does copy as a space, and in monospace contexts usually takes up space. See http://www.cs.tut.fi/~jkorpela/html/nobr.html for a discussion Nr� FT)� max_widthr� r� �break_character)r= �_avoid_word_break_elementsrN r� rW � _break_textr r� ) rl r� r� r� r� r� Z dont_breakZavoidr� r r r r � s* c O s* t | �}t| �}t|f|�|� t||�S )N)r2 r r r )r6 r� r" r� rk r r r r � s c C s> | � � }x0|D ](}t|�|krt|||�}| �||�} qW | S )N)r� �len� _insert_breakr� )rW r� r� �words�word� replacementr r r r� � s r� z[^a-z]c C s� | }d}xrt | �|krz| d |� }tt�|��}|r\|d }|�� |d kr\| d |�� � }||| 7 }| t |�d � } q W || 7 }|S )Nr1 r� � )r� rS �_break_prefer_re�finditerr� )r� �widthr� Z orig_word�resultr� ZbreaksZ last_breakr r r r� � s r� )<r� � __future__r r� r� �urlparser �urllibr � ImportError� urllib.parse�lxmlr Z lxml.htmlr r r r r �unichr� NameError�chr�unicode�strr� �bytes�__all__r� r� �IrO rQ r� r r r rP r� r� ZXPathrM ri r) r r r Z _link_regexesZ_avoid_elementsZ _avoid_hostsZ_avoid_classesr r� r r� Z_avoid_word_break_classesr r r� r� r� r r r r �<module> s� 8 *: &