From 8d7d02f42c3947f756c18cb4d37d9d97fbd0d27d Mon Sep 17 00:00:00 2001 From: Franck Cuny Date: Wed, 10 Aug 2016 14:33:04 -0700 Subject: convert back to md --- posts/2009-06-06-modules-i-like-web-scraper.org | 111 ------------------------ 1 file changed, 111 deletions(-) delete mode 100644 posts/2009-06-06-modules-i-like-web-scraper.org (limited to 'posts/2009-06-06-modules-i-like-web-scraper.org') diff --git a/posts/2009-06-06-modules-i-like-web-scraper.org b/posts/2009-06-06-modules-i-like-web-scraper.org deleted file mode 100644 index bb4a771..0000000 --- a/posts/2009-06-06-modules-i-like-web-scraper.org +++ /dev/null @@ -1,111 +0,0 @@ -For [[http://rtgi.fr][$work]] I need to write scrapers. It used to be -boring and painful. But thanks to -[[http://search.cpan.org/~miyagawa/][miyagawa]], this is not true -anymore. [[http://search.cpan.org/perldoc?Web::Scraper][Web::Scraper]] -offer a nice API: you can write your rules using XPath, you can chaine -rules, a nice and simple syntax, etc. - -I wanted to export my data from my last.fm account but there is no API -for this, so I would need to scrap them. All the data are available -[[http://www.last.fm/user/franckcuny/tracks][as a web page]] that list -your music. So the scraper need to find how many pages, and find the -content on each page to extract a list of your listening. - -For the total of pages, it's easy. Let's take a look at the HTML code -and search for something like this: - -#+BEGIN_EXAMPLE - 272 -#+END_EXAMPLE - -the information is in a class *lastpage*. - -Now we need to find our data: I need the artist name, the song name and -the date I played this song. - -All this data are in a *table*, and each new entry is in a *td*. - -#+BEGIN_EXAMPLE - - [...] - - Earth - Sonar and Depth Charge - - [...] - - 13 May 3:18pm - -#+END_EXAMPLE - -It's simple: information about a song are stored in *subjectcell*, and -the artist and song title are each in a tag *a*. The date is in a -*dateCell*, and we need the *title* from the *abbr* tag. - -The scraper we need to write is - -#+BEGIN_SRC perl - my $scrap = scraper { - process 'a[class="lastpage"]', 'last' => 'TEXT'; - process 'tr', 'songs[]' => scraper { - process 'abbr', 'date' => '@title'; - process 'td[class="subjectCell"]', 'song' => scraper { - process 'a', 'info[]' => 'TEXT'; - }; - } - }; -#+END_SRC - -The first rule extract the total of page. The second iter on each *tr* -and store the content in an array named *songs*. This *tr* need to be -scraped. So we look the the *abbr* tag, and store in *date* the property -*title*. Then we look for the song and artitst information. We look for -the *td* with a class named *subjectCell*, a extract all links. - -Our final script will look like this: - -#+BEGIN_SRC perl - #!/usr/bin/perl -w - use strict; - use feature ':5.10'; - - use Web::Scraper; - use URI; - use IO::All -utf8; - - my $username = shift; - my $output = shift; - - my $scrap = scraper { - process 'a[class="lastpage"]', 'last' => 'TEXT'; - process 'tr', 'songs[]' => scraper { - process 'abbr', 'date' => '@title'; - process 'td[class="subjectCell"]', 'song' => scraper { - process 'a', 'info[]' => 'TEXT'; - }; - } - }; - - my $url = "http://www.last.fm/user/" . $username . "/tracks?page="; - scrap_lastfm(1); - - sub scrap_lastfm { - my $page = shift; - my $scrap_uri = $url . $page; - say $scrap_uri; - my $res = $scrap->scrape(URI->new($scrap_uri)); - my $lastpage = $res->{last}; - foreach my $record (@{$res->{songs}}) { - my $line = join("\t", @{$record->{song}->{info}}, $record->{date}); - $line . "\n" >> io $output; - } - $page++; - scrap_lastfm($page) if $page <= $lastpage; - } -#+END_SRC - -You can use this script like this: - -#+BEGIN_EXAMPLE - % perl lastfmscraper.pl franckcuny store_data.txt -#+END_EXAMPLE -- cgit v1.2.3