html_element() और html_text() की मूल बातें

library(rvest)
page <- read_html('
  <div class="product">
    <h2>  Laptop  </h2>
    <p>Price: <strong>$999</strong></p>
    <p>  Free   shipping  </p>
  </div>
')
# html_text2 trims whitespace intelligently
title <- html_element(page, 'h2')
html_text2(title)  # 'Laptop' (no extra spaces)

# From the whole div - collapses nested text
div <- html_element(page, '.product')
html_text2(div)  # 'Laptop\nPrice: $999\nFree shipping'

library(rvest)
page <- read_html('
  <div>
    <a href="https://example.com" title="Example site">Visit</a>
    <img src="/images/photo.jpg" alt="A photo">
    <div data-price="29.99">Product</div>
  </div>
')
# Extract href from link
link <- html_element(page, 'a')
html_attr(link, 'href')  # 'https://example.com'
html_attr(link, 'title')  # 'Example site'

# Extract src from image
img <- html_element(page, 'img')
html_attr(img, 'src')  # '/images/photo.jpg'

# Extract data attributes
div <- html_element(page, 'div[data-price]')
html_attr(div, 'data-price')  # '29.99'

library(rvest)
page <- read_html('
  <a href="/page" class="nav-link" id="home" data-section="main">Home</a>
')
link <- html_element(page, 'a')

# Get all attributes at once
attrs <- html_attrs(link)
attrs
# href        class        id           data-section
# '/page'     'nav-link'   'home'       'main'

# Access by name
attrs['href']   # '/page'
attrs['class']  # 'nav-link'
names(attrs)    # all attribute names

library(rvest)
page <- read_html('
  <nav>
    <a href="/">Home</a>
    <a href="/about">About</a>
    <span>|</span>
    <a href="/contact">Contact</a>
  </nav>
')
nav <- html_element(page, 'nav')

# Get all direct children
kids <- html_children(nav)
length(kids)  # 4

# Get tag names of children
html_name(kids)  # c('a', 'a', 'span', 'a')

# Filter to only anchor children
links <- kids[html_name(kids) == 'a']
html_text2(links)  # c('Home', 'About', 'Contact')

library(rvest)
page <- read_html('
  <article>
    <h2>Title</h2>
    <p>First paragraph.</p>
    <img src="img.jpg">
    <p>Second paragraph.</p>
  </article>
')
article <- html_element(page, 'article')
all_children <- html_children(article)

# Check tag name of each child
html_name(all_children)
# c('h2', 'p', 'img', 'p')

# Get only paragraph children
paras <- all_children[html_name(all_children) == 'p']
html_text2(paras)
# c('First paragraph.', 'Second paragraph.')

library(rvest)
page <- read_html('
  <div class="card">
    <h3>Laptop</h3>
    <span class="price">$999</span>
  </div>
  <div class="card">
    <h3>Phone</h3>
    <span class="price">$499</span>
  </div>
')
# Get all cards, then extract fields from each
cards <- html_elements(page, '.card')

names_list <- html_text2(html_elements(page, '.card h3'))
prices_list <- html_text2(html_elements(page, '.card .price'))

data.frame(name = names_list, price = prices_list)

library(rvest)
page <- read_html('
  <ul>
    <li><a href="/page1">Page 1</a></li>
    <li><a href="/page2">Page 2</a></li>
    <li><span>No link</span></li>
    <li><a href="/page3">Page 3</a></li>
  </ul>
')
# Get all a elements
links <- html_elements(page, 'a')

# html_attr on a nodeset returns a vector
hrefs <- html_attr(links, 'href')
hrefs  # c('/page1', '/page2', '/page3')

# Link text alongside hrefs
texts <- html_text2(links)
data.frame(text = texts, href = hrefs)

library(rvest)
page <- read_html('
  <div class="product">
    <h3>Widget</h3>
    <!-- No price tag here -->
  </div>
')
# Element exists
title <- html_element(page, 'h3')
html_text2(title)  # 'Widget'

# Element does NOT exist -> NA node
price <- html_element(page, '.price')
html_text2(price)  # NA
is.na(html_text2(price))  # TRUE

# Safe extraction with default
price_text <- html_text2(price)
if (is.na(price_text)) price_text <- 'N/A'
price_text  # 'N/A'

library(rvest)
page <- read_html('
  <div class="book">
    <a href="/book/1" class="title">R Programming</a>
    <span class="author">Hadley Wickham</span>
    <span class="rating" data-stars="5">*****</span>
  </div>
  <div class="book">
    <a href="/book/2" class="title">Advanced R</a>
    <span class="author">Hadley Wickham</span>
    <span class="rating" data-stars="5">*****</span>
  </div>
')
titles  <- html_text2(html_elements(page, '.title'))
authors <- html_text2(html_elements(page, '.author'))
links   <- html_attr(html_elements(page, 'a.title'), 'href')
ratings <- html_attr(html_elements(page, '.rating'), 'data-stars')
data.frame(title=titles, author=authors, link=links, stars=ratings)

library(rvest)
# Core rvest workflow:
# 1. Load page
# page <- read_html(url)

# 2. Find elements
# node  <- html_element(page, 'css-selector')
# nodes <- html_elements(page, 'css-selector')

# 3. Extract content
# html_text2(node)        -> text content
# html_attr(node, 'href') -> attribute value
# html_attrs(node)        -> all attributes
# html_name(node)         -> tag name
# html_children(node)     -> child nodes

# 4. Build data frame
# data.frame(title = html_text2(...), link = html_attr(...))
cat('rvest follows the tidy data philosophy')