Inheritance diagram for duzun\hQuery:

Public Member Functions
	find ($sel, $_attr=NULL, $ctx=NULL)

	find_html ($sel, $attr=NULL, $ctx=NULL)

	find_text ($sel, $attr=NULL, $ctx=NULL)

	index ()

Public Member Functions inherited from duzun\hQuery\HTML_Parser
	__get ($name)

	__set ($name, $value)

	location ($href=NULL)

	baseURI ($href=NULL)
	get/set baseURI

	__construct ($html, $idx=true)

	__toString ()

	url2abs ($url)

	strlen ()

	substr ($start, $length=NULL)

	_info ()
	This method is for debugging only.

	hasClass ($id, $cl)

Public Member Functions inherited from duzun\hQuery\Node
	attr ($attr=NULL, $to_str=false)

	is_empty ()

	isEmpty ()

	isDoc ()

	doc ()

	find ($sel, $attr=NULL)

	exclude ($sel, $attr=NULL)

	__toString ()

	html ($id=NULL)

	outerHtml ($id=NULL)

	text ($id=NULL)

	nodeName ($caseFolding=NULL, $id=NULL)

	pos ($restore=true)

	_children ($ids=NULL, $n=NULL)

	_next ($ids=NULL, $n=0)

	_prev ($ids=NULL, $n=0)

	_all ($ids=NULL)

	_has ($el, $eq=false)
	$el < $this, with $eq == true -> $el <= $this

	_filter_contains ($el, $eq=false)

	__get ($name)

	__set ($name, $value)

	__isset ($name)

	__unset ($name)

	count ()

	current ()

	valid ()

	key ()

	next ()

	prev ()

	rewind ()

Static Public Member Functions
static	fromHTML ($html, $url=NULL)

static	fromFile ($filename, $use_include_path=false, $context=NULL)

static	fromURL ($url, $headers=NULL, $body=NULL, $options=NULL)

static	jsonize ($data, &$type=NULL, $ops=0)

static	unjsonize ($str, &$type=NULL)

static	gz_supported ()

static	gzdecode ($str)

static	do_flock ($fp, $lock, $timeout_ms=384)

static	flock_put_contents ($fn, $cnt, $block=false)

static	flock_get_contents ($fn, $block=false)

static	parse_cookie ($str)

static	http_wr ($host, $head=NULL, $body=NULL, $options=NULL)

Static Public Member Functions inherited from duzun\hQuery\HTML_Parser
static	get_url_base ($url, $array=false)

static	get_url_path ($url)

static	is_url_path ($path)

static	is_abs_path ($path)

static	abs_url ($url, $base)

static	detect_charset ($str)

Static Public Member Functions inherited from duzun\hQuery\Node
static	html_normal_pseudoClass ($p)

static	html_selector2struc ($sel)

static	html_parseAttrStr ($str, $case_folding=true, $extended=false)

static	html_attr2str ($attr, $quote='"')

static	parseCSStr ($str, $case_folding=true)

static	CSSArr2Str ($css)

static	str_range ($comp, $pos=0, $len=NULL)

static	array_select ($arr, $keys, $force_null=false)

static	convert_encoding ($a, $to, $from=NULL)

Public Attributes
	$headers

Public Attributes inherited from duzun\hQuery\Node
const	VERSION = '2.0.2'

	$tag_map

Static Public Attributes
static	$cache_path

static	$cache_expires = 3600

static	$_mockup_class

Static Public Attributes inherited from duzun\hQuery\HTML_Parser
static	$del_spaces = false

static	$case_folding = true

static	$autoclose_tags = false

static	$_emptyTags = array('base','meta','link','hr','br','basefont','param','img','area','input','isindex','col')

static	$_specialTags = array('--'=>'--', '[CDATA['=>']]')

static	$_unparsedTags = array('style', 'script')

static	$_index_attribs = array('href', 'src')

static	$_url_attribs = array('href'=>'href', 'src'=>'src')

Static Public Attributes inherited from duzun\hQuery\Node
static	$last_http_result

static	$selected_doc = NULL

static	$_ar_ = array()

static	$_mi_ = PHP_INT_MAX

static	$_nl_ = NULL

static	$_fl_ = false

static	$_tr_ = true

Static Protected Member Functions
static	serjstype ($str)

static	_gzdecode ($gzdata, $maxlen=NULL)

static	get_cache ($fn, $expire=false, $meta_only=false)

static	set_cache ($fn, $cnt, $meta=NULL, $gzip=true)

Static Protected Member Functions inherited from duzun\hQuery\Node
static	html_findTagClose ($str, $p)

Additional Inherited Members
Protected Member Functions inherited from duzun\hQuery\HTML_Parser
	_index_comments_html ($o)
	Index comment tags position in source HTML.

	_index_all ()

	_get_ctx ($ctx)

	_find ($name, $class=NULL, $attr=NULL, $ctx=NULL, $rec=true)

	_filter ($ids, $name=NULL, $class=NULL, $attr=NULL, $ctx=NULL)

	get_aids_byAttr ($attr, $as_keys=false, $actx=NULL)

	get_aids_byClass ($cl, $as_keys=false, $actx=NULL)

	get_aids_byClassAttr ($cl, $attr, $as_keys=false, $actx=NULL)

	get_ids_byAid ($aid, $sort=true, $has_keys=false)

	get_ids_byAttr ($attr, $sort=true)

	get_ids_byClass ($cl, $sort=true)

	get_ids_byClassAttr ($cl, $attr, $sort=true)

	get_attr_byAid ($aid, $to_str=false)

	get_attr_byId ($id, $attr=NULL, $to_str=false)

Protected Member Functions inherited from duzun\hQuery\Node
	__construct ($doc, $ids, $is_ctx=false)

	_ctx_ids ($ids=NULL)

	_sub_ids ($eq=false)

	_doc_ids ($el, $force_array=true)

	_my_ids ($id=NULL, $keys=false)

	_parent ($ids=NULL, $n=0)

Protected Attributes inherited from duzun\hQuery\HTML_Parser
	$html = ''

	$tags

	$attrs

	$attribs

	$idx_attr

	$tag_idx

	$attr_idx

	$class_idx

	$o = NULL

	$indexed = false

Protected Attributes inherited from duzun\hQuery\Node
	$_prop = array()

	$doc

	$ids

	$exc

Static Protected Attributes inherited from duzun\hQuery\HTML_Parser
static	$_tagID_first_letter = 'a-zA-Z_'

static	$_tagID_letters = 'a-zA-Z_0-9:\-'

static	$_icharset = 'UTF-8'

Detailed Description

Main Class, represents an HTML document.

An extremely fast web scraper that parses megabytes of HTML in a blink of an eye. PHP5+, no dependencies.

API Documentation at https://duzun.github.io/hQuery.php

Author: Dumitru Uzun (DUzun.ME) MIT

Version: 2.0.2

Definition at line 21 of file hQuery.php.

Member Function Documentation

◆ _gzdecode()

static duzun\hQuery::_gzdecode	(	$gzdata,
		$maxlen = `NULL`
	)

staticprotected

Alternative gzdecode() (for PHP < 5.4.0) source: https://github.com/Polycademy/upgradephp/blob/master/upgrade.php

Definition at line 458 of file hQuery.php.

◆ do_flock()

static duzun\hQuery::do_flock	(	$fp,
		$lock,
		$timeout_ms = `384`
	)

static

Lock with retries

Parameters

resource	$fp	- Open file pointer
int	$lock	- Lock type
int	$timeout_ms	- OPTIONAL Timeout to wait for unlock in miliseconds

Returns: true on success, false on fail

Author: Dumitru Uzun

Definition at line 611 of file hQuery.php.

◆ find()

duzun\hQuery::find	(	$sel,
		$_attr = `NULL`,
		$ctx = `NULL`
	)

Finds a collection of nodes inside current document/context (similar to jQuery.fn.find()).

Parameters

string	$sel	- A valid CSS selector (some pseudo-selectors supported).
array \| string	$attr	- OPTIONAL attributes as string or key-value pairs.
hQuery\Node	$ctx	- OPTIONAL the context where to search. If omitted, $this is used.

Returns: hQuery collection of matched elements or NULL

Definition at line 182 of file hQuery.php.

Referenced by duzun\hQuery\HTML_Parser\hasClass().

◆ find_html()

duzun\hQuery::find_html	(	$sel,
		$attr = `NULL`,
		$ctx = `NULL`
	)

Combination of ->find() + ->html()

Parameters

string	$sel	- A valid CSS selector.
array \| string	$attr	- OPTIONAL attributes as string or key-value pairs.
hQuery\Node	$ctx	- OPTIONAL the context where to search. If omitted, $this is used.

Returns: array list of HTML contents of all matched elements

Definition at line 269 of file hQuery.php.

◆ find_text()

duzun\hQuery::find_text	(	$sel,
		$attr = `NULL`,
		$ctx = `NULL`
	)

Combination of ->find() + ->text()

Parameters

string	$sel	- A valid CSS selector.
array \| string	$attr	- OPTIONAL attributes as string or key-value pairs.
hQuery\Node	$ctx	- OPTIONAL the context where to search. If omitted, $this is used.

Returns: array list of Text contents of all matched elements

Definition at line 285 of file hQuery.php.

◆ fromFile()

static duzun\hQuery::fromFile	(	$filename,
		$use_include_path = `false`,
		$context = `NULL`
	)

static

Read the HTML document from a file.

Parameters

string	$filename	- a valid filename
bool	$use_include_path	- OPTIONAL passed to file_get_contents()
resource	$context	- OPTIONAL A valid context resource created with stream_context_create(). See file_get_contents()

Returns: hQuery $doc

Definition at line 67 of file hQuery.php.

◆ fromHTML()

static duzun\hQuery::fromHTML	(	$html,
		$url = `NULL`
	)

static

Parse and HTML string.

Parameters

string	$html	- source of some HTML document
string	$url	- OPTIONAL location of the document. Used for relative URLs inside the document.

Returns: hQuery $doc

Definition at line 41 of file hQuery.php.

◆ fromURL()

static duzun\hQuery::fromURL	(	$url,
		$headers = `NULL`,
		$body = `NULL`,
		$options = `NULL`
	)

static

Fetch the HTML document from remote $url.

Parameters

string	$url	- the URL of the document
array	$headers	- OPTIONAL request headers
array \| string	$body	- OPTIONAL body of the request (for POST or PUT)
array	$options	- OPTIONAL request options (see self::http_wr() for more details)

Returns: hQuery $doc

Definition at line 88 of file hQuery.php.

◆ get_cache()

static duzun\hQuery::get_cache	(	$fn,
		$expire = `false`,
		$meta_only = `false`
	)

staticprotected

Read data from a cache file.

Parameters

string	$fn	- cache filename
int	$expire	- OPTIONAL contents returned only if it is newer then $expire seconds
bool	$meta_only	- OPTIONAL if TRUE, read only meta-info (faster)

Returns: array [mixed <contents>, array <meta_info>]

Definition at line 532 of file hQuery.php.

◆ gz_supported()

static duzun\hQuery::gz_supported ( )

static

Find a function to decode gzip data.

Returns: string A gzip decode function name, or false if not found

Definition at line 435 of file hQuery.php.

◆ gzdecode()

static duzun\hQuery::gzdecode ( $str )

static

gzdecode() (for PHP < 5.4.0)

Definition at line 445 of file hQuery.php.

◆ http_wr()

static duzun\hQuery::http_wr	(	$host,
		$head = `NULL`,
		$body = `NULL`,
		$options = `NULL`
	)

static

Executes a HTTP write-read session.

Parameters

string	$host	- IP/HOST address or URL
array	$head	- list off HTTP headers to be sent along with the request to $host
mixed	$body	- data to be sent as the contents of the request. If is array or object, a http query is built.
array	$options	- list of option as key-value: timeout - connection timeout in seconds host - goes to headers, overrides $host (ex. $host == '127.0.0.1', $options['host'] == 'www.example.com') port - usefull when $host is not a full URL scheme - http, ssl, tls, udp, ... close - whether to close connection o not redirects - number of allowed redirects redirect_method - if (string), this is the new method for redirect request, else if true, preserve method, else use 'GET' on redirect. by default preserve on 307 and 308, GET on 301-303

Returns: array [contents, headers, http-status-code, http-status-message]

Author: Dumitru Uzun

Definition at line 720 of file hQuery.php.

◆ index()

duzun\hQuery::index ( )

Index elements of the source HTML. (Called automatically)

Definition at line 295 of file hQuery.php.

◆ jsonize()

static duzun\hQuery::jsonize	(		$data,
		&	$type = `NULL`,
			$ops = `0`
	)

static

Serialize $data as JSON, fallback to serialize.

Parameters

mixed	$data	- the data to be serialized
	&string	$type - returns the serialization method used ('json' \| 'ser')

Returns: string the serialized data

Definition at line 308 of file hQuery.php.

◆ serjstype()

static duzun\hQuery::serjstype ( $str )

staticprotected

Tries to detect format of $str (json or ser).

Parameters

string $str - JSON encoded or PHP serialized data.

Returns: string 'json' | 'ser', or FALSE on failure to detect format.

Definition at line 414 of file hQuery.php.

◆ set_cache()

static duzun\hQuery::set_cache	(	$fn,
		$cnt,
		$meta = `NULL`,
		$gzip = `true`
	)

staticprotected

Save data to a cache file.

Parameters

string	$fn	- cache filename
mixed	$cnt	- contents to be cached
array	$meta	- OPTIONAL meta information related to contents.
bool	$gzip	- OPTIONAL if TRUE and gzip supported, store contents gzipped

Returns: int|bool On success, number of written bytes, FALSE on fail.

Definition at line 578 of file hQuery.php.

◆ unjsonize()

static duzun\hQuery::unjsonize	(		$str,
		&	$type = `NULL`
	)

static

Unserialize $data from either JSON or serialize.

Parameters

string	$str	- the data to be unserialized
	&string	$type - if not set, returns the serialization method detected ('json' \| 'ser'); if set, forces unjsonize() to use this method for unserialization.

Returns: mixed the unserialized data

Definition at line 332 of file hQuery.php.

The documentation for this class was generated from the following file:

src/hQuery.php

Public Member Functions

Static Public Member Functions

Public Attributes

Static Public Attributes

Static Protected Member Functions

Additional Inherited Members

Detailed Description

Member Function Documentation

◆ _gzdecode()

◆ do_flock()

◆ find()

◆ find_html()

◆ find_text()

◆ fromFile()

◆ fromHTML()

◆ fromURL()

◆ get_cache()

◆ gz_supported()

◆ gzdecode()

◆ http_wr()

◆ index()

◆ jsonize()

◆ serjstype()

◆ set_cache()

◆ unjsonize()