Format: application/x-python-code
1 o
2
3 /'h0] � @ sj d dl Z ddlmZ ddlmZ G dd� de�Zdd� Ze �d e j�Z e �d
4 e j�Z
5 e �d �Z d d
6 � Z dS )� N� )�_BaseHTMLProcessor)�make_safe_absolute_uric s� e Zd Zh d�Zh d�Zh d�Zh d�Zh d�Ze� d�Z
7 h d�Z h d�Z h d �Z
8 h d
9 �Zd Zd Zh d �Zd!� fdd� Z� fdd�Z� fdd�Z� fdd�Zdd� Zdd� Z� fdd�Zd d � Zd"� fd d � Z� ZS )#�_HTMLSanitizer>d �br�codeZul�inputZaudio�outputZmenuz event-sourceZkeygen�bigZspacerZfieldsetZdatalist�tt�pZ
10 figcaptionZoptgroup�soundZlegend�s�spanZcanvasZliZ
11 blockquoteZnoscript�abbr�font�colZh5Zem�var�dfnZimg�sectionZolZmulticol�iZh4�dir�strongZtfoot�map�dtZarea�b�captionZacronym�addressZfigureZaside�sourceZsamp�table�citeZh3�a�div�label�h2ZinsZarticleZvideo�dd�details�header�q�centerZdatagridZmeter�supZkbdZnav�progressZdialog�thZh6�option�h1Zcolgroup�form�dlZnextid�hr�subZtextareaZsmall�strike�trZbutton�pre�time�footer�m�selectZtbodyZthead�command�td�u�del>� ZbordercolorlightZ
12 toppadding�endZcontenteditableZdatafldZloopendZ maxlengthZhreflangZ bordercolor�revZalt�idZdatasrc�hrefZenctype�promptZtabindex�requiredr Zcharoff�nameZgutterZhspaceZ inputmode�shape� autocomplete�coordsZismap�ch�targetr �classZvrml�styleZ
13 galleryimgZ
14 bottompaddingZkeytype�wrapZ loopcount�title�delayZoptimumZ
15 radiogroupZcontrols�heightr �method�scopeZ bgpropertiesZ datapagesize�action�headers�colorZbalance�srczaccept-charset�volumeZ draggableZ cellpaddingZfaceZvspaceZping�openr �rowspan�type�lang�lowZ unselectableZusemapr# Zaxis�for�highZhidden�min�bgcolorZcolspan�nowrap�readonly�clearZdynsrcz
16 repeat-min�xml:langZ accesskey�icon�maxZ autofocus�list�sizeZ leftspacing�dataZ cellspacingz
17 point-sizeZposterZ hidefocus�loopZnohref�frame�border�checkedZpreload�pattern�selectedZlongdesc�summary�variable�widthZ loopstartr/ �
18 backgroundZpqg�acceptZlowsrc�charsetZvalign�char�templateZbordercolordark�stepZnoshadez
19 repeat-max�datetime�rows�start�compact� challenge�replaceZ rightspacing�valueZchoff�disabledZmultiple�urn�relZmedia�default�suppress�cols�rules�align> rK �scriptZapplet>. r rq � font-sizeztext-decorationz white-spaceZazimuthzspeak-punctuationzborder-bottom-colorrb z
20 speak-numeral�display� font-weight� directionz border-colorZpitchrO �
21 font-style�cursorzletter-spacingz line-heightz speech-rateZpausez pause-beforez text-indent�overflowrT z pitch-rangeZstressrV z voice-familyz speak-headerzborder-left-colorz pause-afterzborder-right-color� font-variantZspeak� font-familyz unicode-bidiz
22 text-align�floatzborder-top-colorzvertical-alignZ elevationzbackground-colorzborder-collapseZrichness>' �pointerZcollapse�yellow�rightr` �top�blackZboth�teal�purple�normalZsolid� transparentZfuchsiaZaquaZolive�grayr) �bluez
23 !important�autoZbrownZnavyZdotted�bottom�green�left�red�blockZlime� underlineZdashedZmaroon�italic�none�white�silverZmedium�boldz\^(#[0-9a-f]+|rgb\(\d+%?,\d*%?,?\d*%?\)?|\d{0,2}\.?\d{0,2}(cm|em|ex|in|mm|pc|pt|px|%|,|\))?)$>, ZmscarryZmtdZmsgroupZ maligngroupZmtableZmsqrtZmsrow�moZmrootZmnZmtextZmfracZmfencedZmglyphZmrowZmlongdivZmactionZmtr�
24 annotationZmslineZmspace�miZ
25 munderoverZmover�mathZmerrorZ
26 mmultiscriptsZ semanticsZmsub�msZ mprescriptsZmstackZmunderZmsupZmpaddedZ
27 malignmarkzannotation-xmlZmphantomr� ZmencloseZmsubsupZ mscarriesZ
28 mlabeledtrZmstyle>c z altimg-widthZ
29 linethickness� separatorZlinebreakmultcharZ lineleadingZminsizer� Z mathcolorZ
30 scriptminsizer@ rA Z charalignZbevelledZrspace�
31 xlink:showZinfixlinebreakstyleZ accentunder�otherZ
32 groupalignZ scriptlevelZ columnalignZrowalignZindentalignfirstZindentalignlastZ linebreak� xmlns:xlinkZ
33 columnspacingZ columnwidthZ mathvariant�
34 xlink:hrefrO r ZlinebreakstyleZaltimgZ
35 fontweightZ decimalpointZ
36 rowspacing�
37 xlink:typerU ZvoffsetZ equalcolumnsZ
38 actiontyperW rX ZalttextZ displaystyleZ equalrowsZindentshiftfirstZ framespacingZsuperscriptshiftZminlabelspacingZlargeopZlspace�encodingZ indentshiftZ indentalignZsubscriptshiftZrquoteZ selectionZ
39 denomalignZrowlines�lengthrj Z longdivstyle�xmlnsrq r/ ZalignmentscopeZ
40 stackalign�closeZ indenttargetZstretchy�depthZ fontstyleZ symmetricZ
41 movablelimitsZmathsize�
42 separators�positionZnumalignz
43 altimg-height�locationZside�notationZscriptsizemultiplierr� ZaccentZ columnlinesZ
44 columnspanZfence�shiftZindentshiftlastz
45 altimg-valignZcrossout�edgeZlquoteZmathbackground�maxsizer� ># ZtspanZglyphZanimateTransformZradialGradient�rectZ
46 foreignObjectZpolylineZanimateZ animateColorrM �switchz
47 missing-glyph�setZ
48 animateMotionZdefs�path�svgz font-facezfont-face-nameZlinearGradientZpolygonZuse�marker�circle�stop�metadata�line�descZellipse�g�textr! Zhkernz
49 font-face-srcZmpath>� Z
50 zoomAndPan�stroke-linejoinZ repeatDurr> ZsystemLanguage� fill-opacity�cyZ
51 attributeTyper� Zfx�y1ZdescentZrestartr@ Zryz
52 cap-heightZrequiredFeaturesZpointsz
53 unicode-rangeZrefXzunderline-positionZ markerUnitsz units-per-emZx2r� ZstemvrD �unicodezoverline-position�fillZ
54 alphabeticZ ideographicZslopezstrikethrough-thicknessZ markerWidthZ
55 pathLengthZdyZhanging�widthsrI zx-heightz
56 xlink:actuaterJ zstroke-miterlimitZ
57 visibility�u1�fyZ
58 gradientUnitsZbyzstroke-dashoffsetr� Z repeatCountz stop-opacity�xz xlink:titleZpreserveAspectRatioz
59 marker-midr� �yZbbox�drO z marker-startZstemhzstroke-dasharray�cx�values�to�x1�y2�g2Zadditivezxml:baseZkeyTimesr� �rrT z
60 xlink:role�
61 accumulater� �rxzunderline-thickness�versionrY �fromrZ �contentz arabic-form�stroke-linecapZopacity�stroke-opacityZ baseProfiler^ r� Z transformz
62 accent-heightzpanose-1zhoriz-origin-xrc z
63 marker-endr� z text-anchorre �originz font-stretchz
64 glyph-namer� Z mathematical�rotateZ markerHeightZdxzcolor-rendering�offsetz xml:spacer� zoverline-thicknessZrefYZcalcModeZ
65 attributeNamer� Zorientrq �g1ZrequiredExtensionsZdur� stroke-width�strokeZ keyPoints� fill-rulez horiz-adv-xr� �beginZascentz
66 xlink:arcrole�u2�kz
67 stop-colorZviewBoxZ
68 keySplineszstrikethrough-positionN> r� r� r� r� r� r� r� r� �application/xhtml+xmlc s( t t| ��||� d| _d| _d| _d S �Nr )�superr �__init__�unacceptablestack�mathmlOK�svgOK)�selfr� �_type�� __class__� �JC:\Users\shubh\Videos\agent\nova\Lib\site-packages\feedparser/sanitizer.pyr� � s
69 z_HTMLSanitizer.__init__c s$ t t| ��� d| _d| _d| _d S r� )r� r �resetr� r� r� )r� r� r� r� r� � s
70 z_HTMLSanitizer.resetc
71 s: | j }i }|| jvs
72 | jr�|| jv r| jd7 _| j�d�r8t|��d�s8|dkr/|� d� |dkr8|� d� |dkrGd|v rG| j
73 d7 _
74 |dkrVd|v rV| jd7 _| j
75 rb|| j v rb| j }nZ| jr�|| j
76 v r�| js�dd � | jD �� � fd
77 d �| jD �}� | _d d � |D �| _d
78 d � | j
79 D �� � fdd �| j
80 D �}� | _
81 dd � |D �| _| j}| j�||�}| j}n|| jvr�d S | j
82 s�| jr�tdd� |D ��r�d|vr�|� d� g }| �|�D ]6\}}|dkr�d|v r�| �|�} | r�|� || f� q�||v �r|�||�}|dk�r
83 t|�}|� ||f� q�tt| ��||� d S )Nr �htmlr� r� )r� zhttp://www.w3.org/2000/svgr� )r� z"http://www.w3.org/1998/Math/MathMLc S � g | ]}|� � �qS r� ��lower��.0�attrr� r� r� �
84 <listcomp> � z3_HTMLSanitizer.unknown_starttag.<locals>.<listcomp>c � g | ]}|� vr|�qS r� r� �r r! r r� r� r � c S � i | ]}|� � |�qS r� r r r� r� r� �
85 <dictcomp>
86 � z3_HTMLSanitizer.unknown_starttag.<locals>.<dictcomp>c S r r� r r r� r� r� r r c r r� r� r r r� r� r
87 r
88 c S r r� r r r� r� r� r r
89 c s s" � | ] }|d � d�r|V qdS )r zxlink:N)�
90 startswithr r� r� r� � <genexpr> s � z2_HTMLSanitizer.unknown_starttag.<locals>.<genexpr>)r� z http://www.w3.org/1999/xlinkrK rA )�acceptable_attributes�acceptable_elementsr� �"unacceptable_elements_with_end_tagr� r� �endswith�dict�get�appendr� �mathml_elements�mathml_attributes� svg_elements� svg_attr_map�svg_attributes� svg_elem_map�anyZnormalize_attrs�sanitize_styler r� r �unknown_starttag)
91 r� �tag�attrsr ZkeymapZmixZ clean_attrs�keyr~ Z clean_valuer� r r� r � sd
92
93
94
95
96
97 �
98
99 �z _HTMLSanitizer.unknown_starttagc s� || j vrH|| jv r| jd8 _| jr(|| jv r(|dkr'| jr'| jd8 _n | jrF|| jv rF| j�||�}|dkrE| jrE| jd8 _nd S t t
100 | �� |� d S )Nr r� r� ) r r r� r� r r� r r r r� r �unknown_endtag)r� r r� r� r� r# * s
101
102 ��z _HTMLSanitizer.unknown_endtagc C � d S �Nr� �r� r� r� r� r� � handle_pi9 � z_HTMLSanitizer.handle_pic C r$ r% r� r& r� r� r� � handle_decl< r( z_HTMLSanitizer.handle_declc s | j s
103 tt| ��|� d S d S r% )r� r� r � handle_datar& r� r� r� r* ? s �z_HTMLSanitizer.handle_datac C s t �d��d|�}t �d|�sdS t �dd|��� r dS g }t �d|�D ]Z\}}|s+q$|�� | jv r>|�|d | d � q$|� d �d
104 �� d v ri|� � D ]}|| j
105 vr\| j �|�s\ n qM|�|d | d � q$| j r~|�� | j
106 v r~|�|d | d � q$d�|�S ) Nzurl\s*\(\s*[^\s)]+?\s*\)\s*� z@^([:,;#%.\sa-zA-Z0-9!]|\w-\w|'[\s\w]+'|"[\s\w]+"|\([\d,\s]+\))*$� z\s*[-\w]+\s*:\s*[^:;]*;?z([-\w]+)\s*:\s*([^:;]*)z: �;�-r )rr rk �margin�padding)�re�compiler2 �match�strip�findallr �acceptable_css_propertiesr �split�acceptable_css_keywords�valid_css_valuesr� �acceptable_svg_properties�join)r� rK �clean�propr~ �keywordr� r� r� r C s0
107
108 ����
109 z _HTMLSanitizer.sanitize_styler c sL t t| ��||�}|dkr|S t�d��| j|d �}|r!|�� S t| j�S )Nr z--[^>]*>� ) r� r �
110 parse_commentr1 r2 �search�rawdatar> �len)r� r �report�retr3 r� r� r� r@ c s
111 z _HTMLSanitizer.parse_comment)Nr� )r ) �__name__�
112 __module__� __qualname__r r r r6 r8 r1 r2 r9 r r r r r r r: r� r� r r# r' r) r* r r@ �
113 __classcell__r� r� r� r� r " s6 g 2*�/g' ? r c C s< t ||�}| �dd�} |�| � |�� }|�� �dd�}|S )Nz <![CDATA[z <![CDATA[z
114 �
115 )r r} �feedr r4 )Z html_sourcer� r� r rh r� r� r� �_sanitize_htmlp s
116
117 rL s ^\s*<!ENTITY([^>]*?)>s ^\s*<!DOCTYPE([^>]*?)>s \s+(\w+)\s+"(&#\w+;|[^&"]*)"c C s� t �d| �}|r |�� p
118 d}| d|d � | |d d� }} t�|�}t�d|�}t�|�}|r5|d p6d}d|�� v r@d}nd}d}t|�dkr^|r^d d
119 � |D �}|r^d d � |� d
120 }t�||�| } dd� t
121 �|�D �}|| |fS )z�Strips and replaces the DOCTYPE, returns (rss_version, stripped_data)
122
123 rss_version may be 'rss091n' or None
124 stripped_data is the same XML document with a replaced DOCTYPE
125 s <\w�����Nr � r s netscapeZrss091nc S s g | ] }t �|�r|�qS r� )�RE_SAFE_ENTITY_PATTERNr3 )r �er� r� r� r � s ��z#replace_doctype.<locals>.<listcomp>s <!DOCTYPE feed [
126 <!ENTITYs >
127 <!ENTITY s >
128 ]>c S s" i | ]
129 \}}|� d �|� d ��qS )zutf-8)�decode)r r� �vr� r� r� r � s ��z#replace_doctype.<locals>.<dictcomp>) r1 rA rz �RE_ENTITY_PATTERNr5 r2 �RE_DOCTYPE_PATTERNr rC r; rO ) rh rz �headZentity_resultsZdoctype_results�doctyper� � replacementZ
130 safe_entitiesr� r� r� �replace_doctype� s4 "
131
132 ����
133 rX )
134 r1 r� r �urlsr r rL r2 � MULTILINErS rT rO rX r� r� r� r� �<module> s T
135