Parsing function examples

Practical examples of Custom Parser functions for HTML processing, string manipulation, mathematical operations, and common parsing tasks.

HTML processing

`element_text`

Sample HTML

<!DOCTYPE html>
<html>
<body>
    <div id="product">
        <div id="product-description">This is a nice product</div>
        <div id="product-price">    12  3


        </div>
    </div>
</body>
</html>

Extract text from HTML element and strip whitespaces

{
    "price": {
        "_fns": [
            {
                "_fn": "xpath_one",
                "_args": [".//*[@id='product-price']"]
            },
            {
                "_fn": "element_text"
            }
        ]
    }
}

{
    "price": "12  3"
}

Given a string value as an input, do nothing

{
    "price": {
        "_fns": [
            {
                "_fn": "xpath_one",
                "_args": [".//*[@id='product-price']/text()"]
            },
            {
                "_fn": "element_text"
            }
        ]
    }
}

{
    "price": "    12  3\n\n\n        "
}

`xpath`

Sample HTML

<body>
    <div class="product" id="socks">
        <div class="title">Socks</div>
        <div class="price">123.12</div>
        <div class="description">
            <ul>
                <li class="description-item">Very</li>
                <li class="description-item">Nice</li>
                <li class="description-item">Socks</li>
            </ul>
        </div>
    </div>
</body>

Get all description items

{
    "description_items": {
        "_fns": [
            {
                "_fn": "xpath",
                "_args": ["//li[@class='description-item']/text()"]
            }
        ]
    }
}

{
    "description_items": ["Very", "Nice", "Socks"]
}

Get the first description item

{
    "first_description_item": {
        "_fns": [
            {
                "_fn": "xpath",
                "_args": ["(//li[@class='description-item'])[1]/text()"]
            }
        ]
    }
}

{
    "first_description_item": [
        "Very"
    ]
}

Check if the description section element exists

{
    "description_section_exists": {
        "_fns": [
            {
                "_fn": "xpath",
                "_args": ["boolean(//div[@class='description'])"]
            }
        ]
    }
}

{
    "description_section_exists": true
}

Get price as a number

{
    "price": {
        "_fns": [
            {
                "_fn": "xpath",
                "_args": ["number(//div[@class='price'])"]
            }
        ]
    }
}

{
    "description_section_exists": 123.12
}

Multiple expressions to fallback to in case preceding expression fails

{
    "price": {
        "_fns": [
            {
                "_fn": "xpath",
                "_args": [
                    "//div[@class='product-price']/text()", <--- this does not find anything
                    "//div[@class='price']/text()" <--- this finds the target price
                ]
            }
        ]
    }
}

{
    "price": [
        "123.12"
    ]
}

XPath | operator to match with multiple expressions

{
    "price_and_title": {
        "_fns": [
            {
                "_fn": "xpath",
                "_args": ["//div[@class='price']/text() | //div[@class='title']/text()"]
            }
        ]
    }
}

{
    "price_and_title": [
        "Socks",
        "123.12"
    ]
}

`xpath_one`

Sample HTML

<body>
    <div class="product" id="socks">
        <div class="title">Socks</div>
        <div class="price">123.12</div>
        <div class="description">
            <ul>
                <li class="description-item">Very</li>
                <li class="description-item">Nice</li>
                <li class="description-item">Socks</li>
            </ul>
        </div>
    </div>
</body>

Return the first match

{
    "first_description_item": {
        "_fns": [
            {
                "_fn": "xpath_one",
                "_args": [".//li/text()"]
            }
        ]
    }
}

{
    "first_description_item": "Very"
}

Using XSLT functions

{
    "price": {
        "_fns": [
            {
                "_fn": "xpath_one",
                "_args": ["number(.//div[@class='price'])"]
            }
        ]
    }
}

{
    "price": 123.12
}

String manipulation

`amount_from_string`

Sample HTML

<body>
    <div class="product" id="socks">
        <div class="title">Socks</div>
        <div class="price">The price is: 123.12 pesos</div>
    </div>
</body>

Extract amount from string

{
    "price": {
        "_fns": [
            {
                "_fn": "xpath_one",
                "_args": [".//div[@class='price']/text()"]
            },
            {
                "_fn": "amount_from_string"
            }
        ]
    }
}

{
    "price": 123.12
}

`amount_range_from_string`

Sample HTML

<body>
    <div class="product">
        <div class="price">
            The price is: 123.12 pesos;
            The price is: 345.12 pesos;
            The price is: 678.12 pesos
        </div>
    </div>
</body>

Extract all amounts from string

{
    "prices": {
        "_fns": [
            {
                "_fn": "xpath_one",
                "_args": [".//div[@class='price']/text()"]
            },
            {
                "_fn": "amount_range_from_string"
            }
        ]
    }
}

{    
    "prices": [
        123.12,
        345.12,
        678.12
    ]
}

`join`

Sample HTML

<body>
    <div class="product">
        <div class="price">
            The price is: 123.12 pesos;
        </div>
        <div class="price">
            The price is: 345.12 pesos;
        </div>
        <div class="price">
            The price is: 678.12 pesos
        </div>
    </div>
</body>

Join an array of strings into a single string

{
    "price_variants": {
        "_fns": [
            {
                "_fn": "xpath",
                "_args": [".//div[@class='price']"]
            },
            {  // If we call normalize-space() in first pipeline function, 
               // it will return only the first value.
                "_fn": "xpath",
                "_args": ["normalize-space(text())"]
            },  
            {
                "_fn": "join",
                "_args": ""
            }
        ]
    }
}

{
    "price_variants": "The price is: 123.12 pesos;The price is: 345.12 pesos;The price is: 678.12 pesos"
}

`regex_find_all`

Sample HTML

<body>
    <div class="product">
        <div class="description">
            [one description]
            [two description]
            [three description]
        </div>
    </div>
</body>

Find all matches between two characters

{
    "descriptions": {
        "_fns": [
            {
                "_fn": "xpath_one",
                "_args": [".//div[@class='description']/text()"]
            },
            {
                "_fn": "regex_find_all",
                "_args": ["\\[(.*)\\]"]
            }
        ]
    }
}

{
    "descriptions": [
        "one description",
        "two description",
        "three description"
    ]
}

`regex_search`

Sample HTML

<body>
    <div class="product">
        <div class="description">
            [one description]
            [two description]
            [three description]
            {the one i need}
        </div>
    </div>
</body>

Return description between two characters

{
    "description": {
        "_fns": [
            {
                "_fn": "xpath_one",
                "_args": [".//div[@class='description']/text()"]
            },
            {
                "_fn": "regex_search",
                "_args": ["{(.*)}", 1]
            }
        ]
    }
}

{
    "description": "the one i need"
}

`regex_substring`

Sample HTML

<body>
    <div class="product">
        <div class="description">
            * one description
            * two description
            * three description
            * {this one i would like to get replaced}
        </div>
    </div>
</body>

Replace a part of text with specified value

{
    "descriptions": {
        "_fns": [
            {
                "_fn": "xpath_one",
                "_args": [".//div[@class='description']/text()"]
            },
            {
                "_fn": "regex_substring",
                "_args": ["{this one i would like to get replaced}", "four description"]
            },
            {
                "_fn": "regex_find_all",
                "_args": ["\\*\\s(.*)\n"]
            }
        ]
    }
}

{
    "descriptions": [
        "one description",
        "two description",
        "three description",
        "four description"
    ]
}

Common functions

`convert_to_*`

Sample HTML

<body>
    <div class="product">
        <div class="price">123</div>
        <div class="price">124</div>
        <div class="price">456</div>
        <div class="price">421</div>
        <div class="price">100</div>
    </div>
</body>

Get the count of price variants

{
    "price_variants": {
        "_fns": [
            {
                "_fn": "xpath",
                "_args": [".//div[@class='price']"]
            },
            {
                "_fn": "length"
            }
        ]
    }
}

{
    "price_variants": 5
}

Get the count of price variants in a multi-dimensional array

Sample HTML:

<body>
    <div class="product">
        <property class="colors">
            <option class="color">Red</option>
            <option class="color">Green</option>
            <option class="color">Blue</option>
        </property>
        <property class="sizes">
            <option class="size">S</option>
            <option class="size">M</option>
            <option class="size">L</option>
            <option class="size">XL</option>
        </property>
    </div>
</body>

{
    "number_of_variants": {
        "_fns": [
            {
                "_fn": "xpath",
                "_args": [".//property"]
            },
            {
                "_fn": "xpath",
                "_args": [".//option"]
            },
            {
                "_fn": "length"
            }
        ]
    }
}

{
    "number_of_variants": [
        3,
        3
    ]
}

`select_nth`

Sample HTML

<body>
    <div class="product" id="socks">
        <div class="title">Socks</div>
        <div class="price">123.12</div>
        <div class="description">
            <ul>
                <li class="description-item">Very</li>
                <li class="description-item">Nice</li>
                <li class="description-item">Socks</li>
            </ul>
        </div>
    </div>
</body>

Select the first description item from the array

{
    "price_and_title": {
        "_fns": [
            {
                "_fn": "xpath",
                "_args": ["//li[@class='description-item']/text()"]
            },
            {
                "_fn": "select_nth",
                "_args": 0
            }
        ]
    }
}

{
    "price_and_title": "Very"
}

Select the last description item from the array

{
    "price_and_title": {
        "_fns": [
            {
                "_fn": "xpath",
                "_args": ["//li[@class='description-item']/text()"]
            },
            {
                "_fn": "select_nth",
                "_args": -1
            }
        ]
    }
}

{
    "price_and_title": "Socks"
}

Math functions

`average`

Sample HTML

<body>
    <div class="product">
        <div class="price">123</div>
        <div class="price">124</div>
        <div class="price">456</div>
        <div class="price">421</div>
        <div class="price">100</div>
    </div>
</body>

Find the average of all listed prices

{
    "price_average": {
        "_fns": [
            {
                "_fn": "xpath",
                "_args": [".//div[@class='price']"]
            },
            {
                "_fn": "xpath_one",
                "_args": ["number(text())"]
            },
            {
                "_fn": "average"
            }
        ]
    }
}

{
    "price_average": 244.8
}

`max`

Sample HTML

<body>
    <div class="product">
        <div class="price">123</div>
        <div class="price">124</div>
        <div class="price">456</div>
        <div class="price">421</div>
        <div class="price">100</div>
    </div>
</body>

Find the max of all listed prices

{
    "price_max": {
        "_fns": [
            {
                "_fn": "xpath",
                "_args": [".//div[@class='price']"]
            },
            {
                "_fn": "xpath_one",
                "_args": ["number(text())"]
            },
            {
                "_fn": "max"
            }
        ]
    }
}

{
    "price_max": 456.0
}

`min`

Sample HTML

<body>
    <div class="product">
        <div class="price">123</div>
        <div class="price">124</div>
        <div class="price">456</div>
        <div class="price">421</div>
        <div class="price">100</div>
    </div>
</body>

Find the average of all listed prices

{
    "price_min": {
        "_fns": [
            {
                "_fn": "xpath",
                "_args": [".//div[@class='price']"]
            },
            {
                "_fn": "xpath_one",
                "_args": ["number(text())"]
            },
            {
                "_fn": "min"
            }
        ]
    }
}

{
    "price_min": 100.0
}

`product`

Sample HTML

<body>
    <div class="product">
        <property class="colors">
            <option class="color">Red</option>
            <option class="color">Green</option>
            <option class="color">Blue</option>
        </property>
        <property class="sizes">
            <option class="size">S</option>
            <option class="size">M</option>
            <option class="size">L</option>
            <option class="size">XL</option>
        </property>
    </div>
</body>

Get the count of different product variants

{
    "number_of_variants": {
        "_fns": [
            {
                "_fn": "xpath",
                "_args": [".//property"]
            },
            {
                "_fn": "xpath",
                "_args": [".//option"]
            },
            {
                "_fn": "length"
            },
            {
                "_fn": "product"
            }
        ]
    }
}

{
    "number_of_variants": 12
}

PreviousList of parsing functions NextScheduler

Last updated 1 year ago

Was this helpful?

Good evening

HTML processing

element_text

Sample HTML

xpath

Sample HTML

xpath_one

Sample HTML

String manipulation

amount_from_string

Sample HTML

amount_range_from_string

Sample HTML

join

Sample HTML

regex_find_all

Sample HTML

regex_search

Sample HTML

regex_substring

Sample HTML

Common functions

convert_to_*

Sample HTML

select_nth

Sample HTML

Math functions

average

Sample HTML

max

Sample HTML

min

Sample HTML

product

Sample HTML

`element_text`

`xpath`

`xpath_one`

`amount_from_string`

`amount_range_from_string`

`join`

`regex_find_all`

`regex_search`

`regex_substring`

`convert_to_*`

`select_nth`

`average`

`max`

`min`

`product`