Grabs all LinkedIn urls from a Coursera forum thread. Perfect for the "Let's Connect!" threads.

linkedInLinksPlus.R

require(XML)
require(stringr)

#
# Grabs all names and LinkedIn urls from a Coursera forum thread. Perfect for the "Let's Connect!" threads.
# Usage:
# 1. Open a Coursera forum thread, containing LinkedIn links.
# 2. Scroll all the way to the bottom of the page to load all posts in the thread.
# 3. Save the web page to an html file named post.htm.
# 4. Call linkedInLinks("post.htm")
# 5. To save the result to a file: write.csv(linkedInLinks("post.htm"), "links.csv", quote=FALSE, row.names=FALSE)
#
linkedInLinks <- function(fileName) {
    # Read html page from file.
    data <- htmlTreeParse(fileName, useInternalNodes = T)
    
    # Find all posts containing a LinkedIn url.
    posts <- xpathApply(data, "//div[@class='course-forum-post-view-container' and .//a[contains(@href, 'linkedin')]]")
    
    # Cast each post to an xml document, so that we can parse it.
    postElements <- sapply(posts, function(post) xmlDoc(post))
    
    # Get the author a href elements.
    authorElements <- unlist(sapply(postElements, function(postElement) xpathApply(postElement, "//a[contains(@href, 'forum/profile')]")))
                             
    # Get the author names from each element.
    authors <- sapply(authorElements, xmlValue)
    
    # Find all linkedin links in the comments.
    commentElements <- unlist(sapply(postElements, function(postElement) xpathApply(postElement, "//div[@class='course-forum-post-text']//a[contains(@href, 'linkedin')]")))
    
    # Get the href value for each link.
    links <- sapply(commentElements, function(el) xmlGetAttr(el, "href"))
    
    # Return result.
    data.frame(Name = authors, Url = links)
}