-
-
Save pombredanne/9488388 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env hython | |
; not actually clojure ... | |
(import "urllib2") | |
(import-from "lxml" "html") | |
(defn form-pts-url [developer] | |
"Return the PTS URL for a given developer." | |
(+ "http://qa.debian.org/developer.php?login=" developer)) | |
(defn digest-page [url] | |
"Take a URL and return an lxml.html page ready for scraping." | |
(.fromstring html (.read (.urlopen urllib2 url)))) | |
(defn scrape-page [page] | |
"Scrape the PTS for bugs" | |
(do | |
(def xpath-base "//table[contains(@class, 'packagetable sortable')]") | |
(zip | |
(.xpath page (+ xpath-base "//a[@name]/text()")) | |
(.xpath page (+ xpath-base "//td[2]//a[contains(@href, 'bugs.debian.org')]/text()"))))) | |
(print (scrape-page (digest-page (form-pts-url "paultag")))) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment