V]c @ s` d Z y d d l m Z Wn# e k
r? Z d d l m Z n Xd d l Z d d l Z d d l Z y d d l Z Wn& e k
r Z e
Z e j d n Xd d l m
Z
m Z m Z d Z e j d d k Z e j d Z e j d
Z d Z d e f d
YZ d e f d YZ d e f d YZ d e f d YZ d e f d YZ d e e f d YZ d e f d YZ d e f d YZ d e f d YZ! d e! f d YZ" d e f d! YZ# d" e f d# YZ$ d$ e f d% YZ% d& e f d' YZ& d( e f d) YZ' d* e( f d+ YZ) d S(, t MITi( t CallableNsE The soupsieve package is not installed. CSS selectors cannot be used.( t Formattert
HTMLFormattert XMLFormatters utf-8i i s \S+s \s+c s1 t f d } | j f d } | S( s> Alias one attribute name to another for backward compatibilityc s
t | S( N( t getattr( t self( t attr( s* lib/python2.7/site-packages/bs4/element.pyt alias$ s c s
t | S( N( t setattr( R ( R ( s* lib/python2.7/site-packages/bs4/element.pyR ( s ( t propertyt setter( R R ( ( R s* lib/python2.7/site-packages/bs4/element.pyt _alias" s t NamespacedAttributec B s e Z d d Z RS( c C s{ | d k r! t j | | } n; | d k rB t j | | } n t j | | d | } | | _ | | _ | | _ | S( Nt :( t Nonet unicodet __new__t prefixt namet namespace( t clsR R R t obj( ( s* lib/python2.7/site-packages/bs4/element.pyR 0 s N( t __name__t
__module__R R ( ( ( s* lib/python2.7/site-packages/bs4/element.pyR
. s t% AttributeValueWithCharsetSubstitutionc B s e Z d Z RS( s= A stand-in object for a character encoding specified in HTML.( R R t __doc__( ( ( s* lib/python2.7/site-packages/bs4/element.pyR = s t CharsetMetaAttributeValuec B s e Z d Z d Z d Z RS( s A generic stand-in for the value of a meta tag's 'charset' attribute.
When Beautiful Soup parses the markup '', the
value of the 'charset' attribute will be one of these objects.
c C s t j | | } | | _ | S( N( R R t original_value( R R R ( ( s* lib/python2.7/site-packages/bs4/element.pyR G s c C s | S( N( ( R t encoding( ( s* lib/python2.7/site-packages/bs4/element.pyt encodeL s ( R R R R R ( ( ( s* lib/python2.7/site-packages/bs4/element.pyR @ s t ContentMetaAttributeValuec B s5 e Z d Z e j d e j Z d Z d Z RS( s A generic stand-in for the value of a meta tag's 'content' attribute.
When Beautiful Soup parses the markup:
The value of the 'content' attribute will be one of these objects.
s ((^|;)\s*charset=)([^;]*)c C sM | j j | } | d k r. t j t | St j | | } | | _ | S( N( t
CHARSET_REt searchR R R R ( R R t matchR ( ( s* lib/python2.7/site-packages/bs4/element.pyR [ s c s% f d } | j j | | j S( Nc s | j d S( Ni ( t group( R" ( R ( s* lib/python2.7/site-packages/bs4/element.pyt rewritef s ( R t subR ( R R R$ ( ( R s* lib/python2.7/site-packages/bs4/element.pyR e s ( R R R t ret compilet MR R R ( ( ( s* lib/python2.7/site-packages/bs4/element.pyR P s
t PageElementc B s e Z d Z d) d) d) d) d) d Z d Z d Z e d Z e d Z
e d Z d Z e Z
d Z e Z e Z d Z d
Z e e d Z e Z d Z d
Z d Z d Z d Z d) i d) d Z e Z d) i d) d) d Z e Z d) i d) d Z e Z d) i d) d) d Z! e! Z" e! Z# d) i d) d Z$ e$ Z% d) i d) d) d Z& e& Z' e& Z( d) i d) d Z) e) Z* d) i d) d) d Z+ e+ Z, e+ Z- d) i d Z. e. Z/ d) i d) d Z0 e0 Z1 e0 Z2 e d Z3 e d Z4 d Z5 d Z6 e d Z7 e d Z8 e d! Z9 e d" Z: e d# Z; d$ Z< d% Z= d& Z> d' Z? d( Z@ RS(* se Contains the navigational information for some part of the page
(either a tag or a piece of text)c C s | | _ | | _ | d k r- | | j _ n | | _ | j d k rT | | j _ n | | _ | j d k r{ | | j _ n | d k r | j d k r | j j r | j j d } n | | _ | d k r | | j _ n d S( sN Sets up the initial relations between this element and
other elements.iN( t parentt previous_elementR t next_elementt next_siblingt previous_siblingt contents( R R* R+ R, R. R- ( ( s* lib/python2.7/site-packages/bs4/element.pyt setupo s c C sD | d k r | St | t s1 | j | } n | j | } | S( s2 Format the given string using the given formatter.N( R t
isinstanceR t formatter_for_namet
substitute( R t st formattert output( ( s* lib/python2.7/site-packages/bs4/element.pyt
format_string s c C sO t | t r | S| j r% t } n t } t | rD | d | S| j | S( sd Look up or create a Formatter for the given identifier,
if necessary.
:param formatter: Can be a Formatter object (used as-is), a
function (used as the entity substitution hook for an
XMLFormatter or HTMLFormatter), or a string (used to look up
an XMLFormatter or HTMLFormatter in the appropriate registry.
t entity_substitution( R1 R t _is_xmlR R t callablet REGISTRY( R R5 t c( ( s* lib/python2.7/site-packages/bs4/element.pyR2 s
c C s? | j d k r | j S| j d k r5 t | d t S| j j S( s Is this element part of an XML tree or an HTML tree?
This is used in formatter_for_name, when deciding whether an
XMLFormatter or HTMLFormatter is more appropriate. It can be
inefficient, but it should be called very rarely.
t is_xmlN( t known_xmlR R* R t FalseR9 ( R ( ( s* lib/python2.7/site-packages/bs4/element.pyR9 s
R- R. c C s | j d k r t d n | | k r. d S| | j k rL t d n | j } | j j | } | j | j | | | S( Ns^ Cannot replace one element with another when the element to be replaced is not part of a tree.s% Cannot replace a Tag with its parent.( R* R t
ValueErrort indext extractt insert( R t replace_witht
old_parentt my_index( ( s* lib/python2.7/site-packages/bs4/element.pyRD s
c C sr | j } | j d k r' t d n | j j | } | j x( t | j D] } | j | | qT W| S( NsS Cannot replace an element with its contents when thatelement is not part of a tree.( R* R R@ RA RB t reversedR/ RC ( R t my_parentRF t child( ( s* lib/python2.7/site-packages/bs4/element.pyt unwrap s
c C s | j | } | j | | S( N( RD t append( R t wrap_insidet me( ( s* lib/python2.7/site-packages/bs4/element.pyt wrap s
c C s, | j d k r+ | j j | j j | =n | j } | j } | j d k rm | j | k rm | | j _ n | d k r | | j k r | j | _ n d | _ d | _ d | _ | j d k r | j | j k r | j | j _ n | j d k r| j | j k r| j | j _ n d | _ | _ | S( s0 Destructively rips this element out of the tree.N( R* R R/ RA t _last_descendantR, R+ R. R- ( R t
last_childR, ( ( s* lib/python2.7/site-packages/bs4/element.pyRB s( c C sv | r$ | j d k r$ | j j } n2 | } x) t | t rU | j rU | j d } q- W| rr | | k rr d } n | S( s8 Finds the last element beneath this object to be parsed.iN( R- R R+ R1 t TagR/ ( R t is_initializedt accept_selfRP ( ( s* lib/python2.7/site-packages/bs4/element.pyRO s c C s | d k r t d n | | k r6 t d n t | t rd t | t rd t | } n d d l m } t | | r x1 t | j D] } | j | | | d 7} q Wd St
| t | j } t | d r8| j
d k r8| j
| k r+| j | } | | k r+| d 8} q+n | j n | | _
d } | d k rhd | _ | | _ n8 | j | d } | | _ | | j _ | j t | _ | j d k r| | j _ n | j t } | t | j k r\d | _ | } d } x> | d k r7| d k r7| j } | j
} | d k rPqqW| d k rP| | _ qd | _ n= | j | }
|
| _ | j d k r| | j _ n |
| _ | j d k r| | j _ n | j j | | d S( Ns Cannot insert None into a tag.s Cannot insert a tag into itself.i( t
BeautifulSoupi R* i ( R R@ R1 t
basestringt NavigableStringt bs4RT t listR/ RC t mint lent hasattrR* RA RB R. R+ R- RO R? R, ( R t positiont new_childRT t subchildt
current_indext previous_childt new_childs_last_elementR* t parents_next_siblingt
next_child( ( s* lib/python2.7/site-packages/bs4/element.pyRC
sh
c C s | j t | j | d S( s2 Appends the given tag to the contents of this tag.N( RC RZ R/ ( R t tag( ( s* lib/python2.7/site-packages/bs4/element.pyRK W s c C s" x | D] } | j | q Wd S( s3 Appends the given tags to the contents of this tag.N( RK ( R t tagsRd ( ( s* lib/python2.7/site-packages/bs4/element.pyt extend[ s
c s j } | d k r$ t d n t f d | D rO t d n xI | D]A } t | t rx | j n | j } | j | | qV Wd S( s Makes the given element(s) the immediate predecessor of this one.
The elements will have the same parent, and the given elements
will be immediately before this one.
s2 Element has no parent, so 'before' has no meaning.c 3 s | ] } | k Vq d S( N( ( t .0t x( R ( s* lib/python2.7/site-packages/bs4/element.pys j s s& Can't insert an element before itself.N( R* R R@ t anyR1 R) RB RA RC ( R t argsR* t predecessorRA ( ( R s* lib/python2.7/site-packages/bs4/element.pyt
insert_before` s
c s j } | d k r$ t d n t f d | D rO t d n d } x[ | D]S } t | t r~ | j n | j } | j | d | | | d 7} q\ Wd S( s Makes the given element(s) the immediate successor of this one.
The elements will have the same parent, and the given elements
will be immediately after this one.
s1 Element has no parent, so 'after' has no meaning.c 3 s | ] } | k Vq d S( N( ( Rg Rh ( R ( s* lib/python2.7/site-packages/bs4/element.pys s s% Can't insert an element after itself.i i N( R* R R@ Ri R1 R) RB RA RC ( R Rj R* t offsett successorRA ( ( R s* lib/python2.7/site-packages/bs4/element.pyt insert_aftert s
c K s | j | j | | | | S( sj Returns the first item that matches the given criteria and
appears after this Tag in the document.( t _find_onet
find_all_next( R R t attrst textt kwargs( ( s* lib/python2.7/site-packages/bs4/element.pyt find_next s c K s | j | | | | | j | S( sb Returns all items that match the given criteria and appear
after this Tag in the document.( t _find_allt
next_elements( R R Rr Rs t limitRt ( ( s* lib/python2.7/site-packages/bs4/element.pyRq s c K s | j | j | | | | S( s{ Returns the closest sibling to this Tag that matches the
given criteria and appears after this Tag in the document.( Rp t find_next_siblings( R R Rr Rs Rt ( ( s* lib/python2.7/site-packages/bs4/element.pyt find_next_sibling s c K s | j | | | | | j | S( sq Returns the siblings of this Tag that match the given
criteria and appear after this Tag in the document.( Rv t
next_siblings( R R Rr Rs Rx Rt ( ( s* lib/python2.7/site-packages/bs4/element.pyRy s c K s | j | j | | | | S( sk Returns the first item that matches the given criteria and
appears before this Tag in the document.( Rp t find_all_previous( R R Rr Rs Rt ( ( s* lib/python2.7/site-packages/bs4/element.pyt
find_previous s c K s | j | | | | | j | S( sc Returns all items that match the given criteria and appear
before this Tag in the document.( Rv t previous_elements( R R Rr Rs Rx Rt ( ( s* lib/python2.7/site-packages/bs4/element.pyR| s c K s | j | j | | | | S( s| Returns the closest sibling to this Tag that matches the
given criteria and appears before this Tag in the document.( Rp t find_previous_siblings( R R Rr Rs Rt ( ( s* lib/python2.7/site-packages/bs4/element.pyt find_previous_sibling s c K s | j | | | | | j | S( sr Returns the siblings of this Tag that match the given
criteria and appear before this Tag in the document.( Rv t previous_siblings( R R Rr Rs Rx Rt ( ( s* lib/python2.7/site-packages/bs4/element.pyR s c K s5 d } | j | | d | } | r1 | d } n | S( sO Returns the closest parent of this Tag that matches the given
criteria.i i N( R t find_parents( R R Rr Rt t rt l( ( s* lib/python2.7/site-packages/bs4/element.pyt find_parent s
c K s | j | | d | | j | S( sF Returns the parents of this Tag that match the given
criteria.N( Rv R t parents( R R Rr Rx Rt ( ( s* lib/python2.7/site-packages/bs4/element.pyR s c C s | j S( N( R, ( R ( ( s* lib/python2.7/site-packages/bs4/element.pyt next s c C s | j S( N( R+ ( R ( ( s* lib/python2.7/site-packages/bs4/element.pyt previous s c K s5 d } | | | | d | } | r1 | d } n | S( Ni i ( R ( R t methodR Rr Rs Rt R R ( ( s* lib/python2.7/site-packages/bs4/element.pyRp s
c s | d k r, d | k r, | d } | d =n t t rD } n t | | | } | d k r&| r&| r&| r& t k s d k r d | D } t | | St t r& j d d k r j d d \ n d f d | D } t | | Sn t | } xy t ry t | }
Wn t k
r_Pn X|
r5| j
|
} | r| j | | rt | | k rPqqq5q5W| S( s8 Iterates over a generator looking for things that match.t stringc s s$ | ] } t | t r | Vq d S( N( R1 RQ ( Rg t element( ( s* lib/python2.7/site-packages/bs4/element.pys s R i c 3 s] | ]S } t | t r' | j k sQ | j k r d k sQ | j k r | Vq d S( N( R1 RQ R R R ( Rg R ( t
local_nameR R ( s* lib/python2.7/site-packages/bs4/element.pys s
N(
R R1 t SoupStrainert Truet ResultSetRU t countt splitR t
StopIterationR! RK RZ ( R R Rr Rs Rx t generatorRt t strainert resultt resultst it found( ( R R R s* lib/python2.7/site-packages/bs4/element.pyRv s<
!
c c s. | j } x | d k r) | V| j } q Wd S( N( R, R ( R R ( ( s* lib/python2.7/site-packages/bs4/element.pyRw & s c c s. | j } x | d k r) | V| j } q Wd S( N( R- R ( R R ( ( s* lib/python2.7/site-packages/bs4/element.pyR{ - s c c s. | j } x | d k r) | V| j } q Wd S( N( R+ R ( R R ( ( s* lib/python2.7/site-packages/bs4/element.pyR~ 4 s c c s. | j } x | d k r) | V| j } q Wd S( N( R. R ( R R ( ( s* lib/python2.7/site-packages/bs4/element.pyR ; s c c s. | j } x | d k r) | V| j } q Wd S( N( R* R ( R R ( ( s* lib/python2.7/site-packages/bs4/element.pyR B s c C s | j S( N( Rw ( R ( ( s* lib/python2.7/site-packages/bs4/element.pyt
nextGeneratorK s c C s | j S( N( R{ ( R ( ( s* lib/python2.7/site-packages/bs4/element.pyt nextSiblingGeneratorN s c C s | j S( N( R~ ( R ( ( s* lib/python2.7/site-packages/bs4/element.pyt previousGeneratorQ s c C s | j S( N( R ( R ( ( s* lib/python2.7/site-packages/bs4/element.pyt previousSiblingGeneratorT s c C s | j S( N( R ( R ( ( s* lib/python2.7/site-packages/bs4/element.pyt parentGeneratorW s N(A R R R R R0 R7 R2 R
R9 R t nextSiblingt previousSiblingRD t replaceWithRJ t replace_with_childrent replaceWithChildrenRN RB R RO t _lastRecursiveChildRC RK Rf Rl Ro Ru t findNextRq t findAllNextRz t findNextSiblingRy t findNextSiblingst fetchNextSiblingsR} t findPreviousR| t findAllPrevioust
fetchPreviousR t findPreviousSiblingR t findPreviousSiblingst fetchPreviousSiblingsR t
findParentR t findParentst fetchParentsR R Rp Rv Rw R{ R~ R R R R R R R ( ( ( s* lib/python2.7/site-packages/bs4/element.pyR) k sz J
6 RV c B sk e Z d Z d Z d Z d Z d Z d Z d Z d d Z
e d Z e j
d Z RS(
t c C sG t | t r$ t j | | } n t j | | t } | j | S( s- Create a new NavigableString.
When unpickling a NavigableString, this method is called with
the string in DEFAULT_OUTPUT_ENCODING. That encoding needs to be
passed in to the superclass's __new__ or the superclass won't know
how to handle non-ASCII characters.
( R1 R R t DEFAULT_OUTPUT_ENCODINGR0 ( R t valuet u( ( s* lib/python2.7/site-packages/bs4/element.pyR e s
c C s t | | S( s A copy of a NavigableString has the same contents and class
as the original, but it is not connected to the parse tree.
( t type( R ( ( s* lib/python2.7/site-packages/bs4/element.pyt __copy__t s c C s
t | f S( N( R ( R ( ( s* lib/python2.7/site-packages/bs4/element.pyt __getnewargs__z s c C s0 | d k r | St d | j j | f d S( s text.string gives you text. This is for backwards
compatibility for Navigable*String, but for CData* it lets you
get the string without the CData wrapper.R s! '%s' object has no attribute '%s'N( t AttributeErrort __class__R ( R R ( ( s* lib/python2.7/site-packages/bs4/element.pyt __getattr__} s
t minimalc C s$ | j | | } | j | | j S( s. Run the string through the provided formatter.( R7 t PREFIXt SUFFIX( R R5 R6 ( ( s* lib/python2.7/site-packages/bs4/element.pyt output_ready s c C s d S( N( R ( R ( ( s* lib/python2.7/site-packages/bs4/element.pyR s c C s t d d S( Ns) A NavigableString cannot be given a name.( R ( R R ( ( s* lib/python2.7/site-packages/bs4/element.pyR s N( R R R R R R> R R R R R R
R R ( ( ( s* lib/python2.7/site-packages/bs4/element.pyRV [ s t PreformattedStringc B s e Z d Z d d Z RS( s A NavigableString not subject to the normal formatting rules.
The string will be passed into the formatter (to trigger side effects),
but the return value will be ignored.
c C s3 | d k r! | j | | } n | j | | j S( sw CData strings are passed into the formatter, purely
for any side effects. The return value is ignored.
N( R R7 R R ( R R5 t ignore( ( s* lib/python2.7/site-packages/bs4/element.pyR s N( R R R R R ( ( ( s* lib/python2.7/site-packages/bs4/element.pyR s t CDatac B s e Z d Z d Z RS( u ( R R R R ( ( ( s* lib/python2.7/site-packages/bs4/element.pyR s t ProcessingInstructionc B s e Z d Z d Z d Z RS( s A SGML processing instruction.u ( R R R R R ( ( ( s* lib/python2.7/site-packages/bs4/element.pyR s t XMLProcessingInstructionc B s e Z d Z d Z d Z RS( s An XML processing instruction.u ( R R R R R ( ( ( s* lib/python2.7/site-packages/bs4/element.pyR s t Commentc B s e Z d Z d Z RS( u ( R R R R ( ( ( s* lib/python2.7/site-packages/bs4/element.pyR s t Declarationc B s e Z d Z d Z RS( u ( R R R R ( ( ( s* lib/python2.7/site-packages/bs4/element.pyR s t Doctypec B s# e Z e d Z d Z d Z RS( c C sm | p d } | d k rF | d | 7} | d k rc | d | 7} qc n | d k rc | d | 7} n t | S( NR s PUBLIC "%s"s "%s"s SYSTEM "%s"( R R ( R R t pub_idt system_idR ( ( s* lib/python2.7/site-packages/bs4/element.pyt for_name_and_ids s u
( R R t classmethodR R R ( ( ( s* lib/python2.7/site-packages/bs4/element.pyR s RQ c
B s e Z d Z d5 d5 d5 d5 d5 d5 d5 d5 d5 d Z e d Z d Z e d Z e Z
e d Z e j d Z e
e e f d Z e e Z e d Z d e
e e f d
Z e Z e e Z d Z e
d Z d
Z d Z d5 d Z d5 d Z d Z d Z d Z d Z d Z d Z! d Z" d Z# d Z$ d Z% d Z& d Z' d Z( d d Z) d Z* d! Z+ e, re* Z+ Z) n e- d5 d" d# d$ Z. d5 e- d" d% Z/ d& Z0 d5 d" d' Z1 d5 e- d" d( Z2 d5 e- d" d) Z3 e- e
d* d+ Z4 d5 i e5 d5 d, Z6 e6 Z7 d5 i e5 d5 d5 d- Z8 e8 Z9 e8 Z: e d. Z; e d/ Z< d5 d0 Z= d5 d5 d1 Z> d2 Z? d3 Z@ d4 ZA RS(6 s= Represents a found HTML tag with its attributes and contents.c
C sb | d k r d | _ n | j | _ | d k r? t d n | | _ | | _ | | _ | d k ro i } nN | r | d k r | j r | j | j | } q t | } n t | } | r | j
| _ n | | _ | | _ g | _
| j | | t | _ | d k r't | _ d | _ n7 | j | | j | | _ | j | _ | j | _ d S( s Basic constructor.s% No value provided for new tag's name.N( R t parser_classR R@ R R R t cdata_list_attributest$ _replace_cdata_list_attribute_valuest dictR= R> Rr R/ R0 R? t hiddent can_be_empty_elementt set_up_substitutionst preserve_whitespace_tags(
R t parsert builderR R R Rr R* R R= ( ( s* lib/python2.7/site-packages/bs4/element.pyt __init__ s<
R c C s t | d | j | j | j | j | j d | j } x' d D] } t | | t | | q@ Wx$ | j
D] } | j | j qm W| S( s A copy of a Tag is a new Tag, unconnected to the parse tree.
Its contents are a copy of the old Tag's contents.
R= R R N( R R (
R R R R R R Rr R9 R R R/ RK R ( R t cloneR RI ( ( s* lib/python2.7/site-packages/bs4/element.pyR s
c C s t | j d k o | j S( s7 Is this tag an empty-element tag? (aka a self-closing tag)
A tag that has contents is never an empty-element tag.
A tag that has no contents may or may not be an empty-element
tag. It depends on the builder used to create the tag. If the
builder has a designated list of empty-element tags, then only
a tag whose name shows up in that list is considered an
empty-element tag.
If the builder has no designated list of empty-element tags,
then any tag with no contents is an empty-element tag.
i ( RZ R/ R ( R ( ( s* lib/python2.7/site-packages/bs4/element.pyt is_empty_element# s c C s@ t | j d k r d S| j d } t | t r9 | S| j S( sq Convenience property to get the single string within this tag.
:Return: If this tag has a single string child, return value
is that string. If this tag has no children, or more than one
child, return value is None. If this tag has one child tag,
return value is the 'string' attribute of the child tag,
recursively.
i i N( RZ R/ R R1 RV R ( R RI ( ( s* lib/python2.7/site-packages/bs4/element.pyR 5 s
c C s$ | j | j | j | d S( N( t clearRK R ( R R ( ( s* lib/python2.7/site-packages/bs4/element.pyR F s
c c s x | j D]x } | d k r, t | t s
| d k rP t | | k rP q
n | r} | j } t | d k r} q
q} n | Vq
Wd S( s Yield all strings of certain classes, possibly stripping them.
By default, yields only NavigableString and CData objects. So
no comments, processing instructions, etc.
i N( t descendantsR R1 RV R t stripRZ ( R R t typest
descendant( ( s* lib/python2.7/site-packages/bs4/element.pyt _all_stringsK s c c s# x | j t D] } | Vq Wd S( N( R R ( R R ( ( s* lib/python2.7/site-packages/bs4/element.pyt stripped_strings_ s u c C s/ | j g | j | d | D] } | ^ q S( sP
Get all child strings, concatenated using the given separator.
R ( t joinR ( R t separatorR R R4 ( ( s* lib/python2.7/site-packages/bs4/element.pyt get_textd s c C sL | j | } x5 | d k rG | j } | j j g | _ | } q Wd S( s/ Recursively destroys the contents of this tree.N( RB R R, t __dict__R R/ ( R R R ( ( s* lib/python2.7/site-packages/bs4/element.pyt decomposen s
c C sg | rD xZ | j D], } t | t r3 | j q | j q Wn x | j D] } | j qO Wd S( sP
Extract all children. If decompose is True, decompose instead.
N( R/ R1 RQ R RB ( R R R ( ( s* lib/python2.7/site-packages/bs4/element.pyR x s
c C s g } x t | j D] \ } } t | t r> | j n | t | j d k r] q n | j | d } t | t r t | t r t | t r t | t r | j | q q WxY t | D]K } | j | } | j | d } | j
t | | } | j | q Wd S( s Smooth out this element's children by consolidating consecutive strings.
This makes pretty-printed output look more natural following a
lot of operations that modified the tree.
i N( t enumerateR/ R1 RQ t smoothRZ RV R RK RG RB RD ( R t markedR t at bt n( ( s* lib/python2.7/site-packages/bs4/element.pyR s$
c C s@ x- t | j D] \ } } | | k r | Sq Wt d d S( s
Find the index of a child by identity, not value. Avoids issues with
tag.contents.index(element) getting the index of equal elements.
s Tag.index: element not in tagN( R R/ R@ ( R R R RI ( ( s* lib/python2.7/site-packages/bs4/element.pyRA s c C s | j j | | S( s Returns the value of the 'key' attribute for the tag, or
the value given for 'default' if it doesn't have that
attribute.( Rr t get( R t keyt default( ( s* lib/python2.7/site-packages/bs4/element.pyR s c C s1 | j | | } t | t s- | g } n | S( s- The same as get(), but always returns a list.( R R1 RX ( R R R R ( ( s* lib/python2.7/site-packages/bs4/element.pyt get_attribute_list s c C s
| | j k S( N( Rr ( R R ( ( s* lib/python2.7/site-packages/bs4/element.pyt has_attr s c C s t | j S( N( t strt __hash__( R ( ( s* lib/python2.7/site-packages/bs4/element.pyR s c C s | j | S( sq tag[key] returns the value of the 'key' attribute for the tag,
and throws an exception if it's not there.( Rr ( R R ( ( s* lib/python2.7/site-packages/bs4/element.pyt __getitem__ s c C s
t | j S( s0 Iterating over a tag iterates over its contents.( t iterR/ ( R ( ( s* lib/python2.7/site-packages/bs4/element.pyt __iter__ s c C s
t | j S( s: The length of a tag is the length of its list of contents.( RZ R/ ( R ( ( s* lib/python2.7/site-packages/bs4/element.pyt __len__ s c C s
| | j k S( N( R/ ( R Rh ( ( s* lib/python2.7/site-packages/bs4/element.pyt __contains__ s c C s t S( s- A tag is non-None even if it has no contents.( R ( R ( ( s* lib/python2.7/site-packages/bs4/element.pyt __nonzero__ s c C s | | j | tag that mentions the document's
encoding.
t t =R R s i s
<%s%s%s%s>s
iN( R1 R R2 t
attributesR RX t tupleR RU R R R t attribute_valuet quoted_attribute_valueRK R R t void_element_close_prefixR t _should_pretty_printt decode_contentsR R- ( R R t eventual_encodingR5 R Rr R t valt decodedRs t closet closeTagR t pretty_printt spacet indent_spacet indent_contentsR/ R4 t attribute_string( ( s* lib/python2.7/site-packages/bs4/element.pyR 1 st
c C s | d k o | j | j k S( s" Should this tag be pretty-printed?N( R R R ( R R ( ( s* lib/python2.7/site-packages/bs4/element.pyR s c C s9 | d k r | j t d | S| j | t d | Sd S( NR5 ( R R R R ( R R R5 ( ( s* lib/python2.7/site-packages/bs4/element.pyt prettify s c C s; t | t s! | j | } n | d k } g } x | D] } d } t | t rg | j | } n. t | t r | j | j | | | n | j o | j
| j k } | r | r | r | j } n | r: | r | r | j d | d n | j | | r*| r*| j d q*q: q: Wd j | S( st Renders the contents of this tag as a Unicode string.
:param indent_level: Each line of the rendering will be
indented this many spaces.
:param eventual_encoding: The tag is destined to be
encoded into this encoding. decode_contents() is _not_
responsible for performing that encoding. This information
is passed in so that it can be substituted in if the
document contains a tag that mentions the document's
encoding.
:param formatter: A Formatter object, or a string naming one of
the standard Formatters.
R i s
R N(
R1 R R2 R RV R RQ RK R R R R R ( R R R R5 R R4 R< Rs t preserve_whitespace( ( s* lib/python2.7/site-packages/bs4/element.pyR s*
c C s" | j | | | } | j | S( sc Renders the contents of this tag as a bytestring.
:param indent_level: Each line of the rendering will be
indented this many spaces.
:param eventual_encoding: The bytestring will be in this encoding.
:param formatter: The output formatter responsible for converting
entities to Unicode characters.
( R R ( R R R R5 R/ ( ( s* lib/python2.7/site-packages/bs4/element.pyt encode_contents s i c C s% | s d } n | j d | d | S( NR R ( R R% ( R R t prettyPrintt indentLevel( ( s* lib/python2.7/site-packages/bs4/element.pyt renderContents s c K s; d } | j | | | | d | } | r7 | d } n | S( sL Return only the first child of this Tag matching the given
criteria.i i N( R R ( R R Rr t recursiveRs Rt R R ( ( s* lib/python2.7/site-packages/bs4/element.pyR s
c K s7 | j } | s | j } n | j | | | | | | S( s Extracts a list of Tag objects that match the given
criteria. You can specify the name of the Tag and any
attributes you want the Tag to have.
The value of a key-value pair in the 'attrs' map can be a
string, a list of strings, a regular expression object, or a
callable that takes a string and returns whether or not the
string matches for some custom definition of 'matches'. The
same is true of the tag name.( R t childrenRv ( R R Rr R) Rs Rx Rt R ( ( s* lib/python2.7/site-packages/bs4/element.pyR s c C s
t | j S( N( R R/ ( R ( ( s* lib/python2.7/site-packages/bs4/element.pyR* s c c sT t | j s d S| j j } | j d } x | | k rO | V| j } q2 Wd S( Ni ( RZ R/ RO R, ( R t stopNodet current( ( s* lib/python2.7/site-packages/bs4/element.pyR s
c K s* | j | | d | } | r& | d Sd S( s9 Perform a CSS selection operation on the current element.i i N( t selectR ( R t selectort
namespacesRt R ( ( s* lib/python2.7/site-packages/bs4/element.pyt
select_one s c K sa | d k r | j } n | d k r- d } n t d k rH t d n t j | | | | | S( s: Perform a CSS selection operation on the current element.
This uses the SoupSieve library.
:param selector: A string containing a CSS selector.
:param namespaces: A dictionary mapping namespace prefixes
used in the CSS selector to namespace URIs. By default,
Beautiful Soup will use the prefixes it encountered while
parsing the document.
:param limit: After finding this number of results, stop looking.
:param kwargs: Any extra arguments you'd like to pass in to
soupsieve.select().
i sL Cannot execute CSS selectors because the soupsieve package is not installed.N( R t _namespacest soupsievet NotImplementedErrorR- ( R R. R/ Rx Rt ( ( s* lib/python2.7/site-packages/bs4/element.pyR- s c C s | j S( N( R* ( R ( ( s* lib/python2.7/site-packages/bs4/element.pyt childGenerator9 s c C s | j S( N( R ( R ( ( s* lib/python2.7/site-packages/bs4/element.pyt recursiveChildGenerator< s c C s t j d | | j | S( s This was kind of misleading because has_key() (attributes)
was different from __in__ (contents). has_key() is gone in
Python 3, anyway.s2 has_key is deprecated. Use has_attr("%s") instead.( R R R ( R R ( ( s* lib/python2.7/site-packages/bs4/element.pyt has_key? s N(B R R R R R R t parserClassR R
R t
isSelfClosingR R R? RV R R t stringsR R t getTextRs R R R RA R R R R R R R R R R R R R R R R
R R R R R R R R# R R% R( R R t findChildR t findAllt findChildrenR* R R0 R- R4 R5 R6 ( ( ( s* lib/python2.7/site-packages/bs4/element.pyRQ s >
%
] , R c B s\ e Z d Z d i d d Z d Z d Z d i d Z e Z d Z d d Z
RS( sM Encapsulates a number of ways of matching a markup element (tag or
text).c K s | j | | _ t | t s4 | | d sL : y