Basic commands and explanation for HTML parsing with the Java library Jsoup using CSS or Jquery-like Selectors
|
*
|
All elements
|
document.select("*")
|
|
tagname
|
Find elements by tag
|
document.select("h1")
|
|
#id
|
Find elements by ID
|
document.select("#subtitle")
|
|
.class
|
Find elements by class name
|
document.select(".list")
|
|
[attributre]
|
Elements with attribute
|
document.select("[href]")
|
|
[^attr]
|
Elements with an attribute name prefix
|
document.select("[^data-]")
|
|
[attr=value]
|
Elements with an attribute value
|
document.select("[width=100]")
|
|
[attr^=value]
|
Elements with attributes that start with...
|
document.select("[class^=button]")
|
|
[attr$=value]
|
Elements with attributes that end with...
|
document.select("[href$=example.com]")
|
|
[attr*=value]
|
Elements with attributes that contains the value...
|
document.select("[class*=button]")
|
|
[attr~=regex]
|
Elements with attributes that match the regular expression
|
document.select("img[src~=(?i)\\.(png|jpe?g)]")
|
|
:lt(n)
|
Find elements whose siblings index is less than n
|
document.select("td:lt(3)")
|
|
:gt(n)
|
Find elements whose sibling index is greater than n
|
document.select("td:gt(2)")
|
|
:eq(n)
|
Find elements whose sibling index is equal to n
|
document.select("td:eq(2)")
|
|
:has(selector)
|
Find elements that contain elements matching the selector
|
document.select("li:has(a)")
|
|
:not(selector)
|
Find elements that do not match the selector
|
document.select("li:not(#justLink)")
|
|
:contains(text)
|
Find element that contain the given text. (case-sesitive)
|
document.select(":contains(world)")
|
|
:contains(text)
|
Find elements that directly contain the given text
|
document.select(":containsOwn(world)
|
|
:matches(regex)
|
Find elements whose text matches the specified regular expression
|
document.select(":matches(^Button 1$)")
|
|
:matchesOwn(regex)
|
Find elements whose own text matches the spicified regular expression
|
document.select(":matchesOwn(1)")
|
|
el#id
|
Element with ID
|
document.select("li#justLink")
|
|
el.class
|
Elements with class
|
document.select("li.sale")
|
|
el[attr]
|
Elements with attribute
|
document.select("li[data-price]")
|
|
el[attr][attr].class ...
|
Any combination
|
document.select("img[src][width]")
|
|
ancestor child
|
Child elements that descend form ancestor
|
document.select("ul li a")
|
|
parent > child
|
Child elements that descend directly from parent
|
document.select("body > ul > li > ul > li > a")
|
|
siblingA + siblingB
|
Sibling B element immediately preceded by sibling A
|
document.select(".child1 + .child2")
|
|
siblingA ~ siblingB
|
Sibling X element preceded by Sibling A
|
document.select(".child1 ~ div")
|
|
el, el, el ...
|
Unique elements that match any of the selectors
|
document.select("div.masthead, div.logo")
|
No comments yet.
Cheatography n. The art of mapping complex subjects into clear, instantly navigable reference guides.
