#!/usr/bin/env python # # this script is in the public domain. # some documentation at http://www.nenie.org/misc/bbcradio/ # # history # 200501 added support for getting into frames that have been added into BBC player # import sys import string import re import urllib import urlparse def a_link (href, a_label): "A link, extract label from scheme if no label" if a_label == None or a_label == "": i = string.find (href, ':') if i >= 0: a_label = href[:i] return '' + a_label + '' def tag (a_tag, a_content): "XML tag" return '<' + a_tag + '>' + a_content + '\n' def embed_src (a_line): "Extract src attribute from embed tag" result = "" if string.find (a_line, "

= 0: m = re.search ("""

""", a_line) if m != None: a_player_url_tag = m.group(2) a_player_url = m.group (1)+a_player_url_tag a_url = urlparse.urljoin (a_base_url, a_player_url) a_ra = urlparse.urljoin (a_base_url, retrieve_bbc_realaudio (a_url)) if a_ra: a_rtp = retrieve_realaudio_target (a_ra) result = (a_player_url_tag, a_ra, a_rtp) return result def textify_img (a_line): "Replace img tags with their alt text" s = re.sub ("""

]*alt="" />""", """""", a_line) return re.sub ("""]* alt=['"]([^'"]*)['"][^>]*>""", """[\\1]""", s) def absolute_href (a_base_url, a_line): "Replace href links with absolute links" f = lambda m,b=a_base_url: 'href="' + urlparse.urljoin (b, m.group(1)) + '"' return re.sub ("""[hH][rR][eE][fF]=['"]([^'"]*)['"]""", f, a_line) def process_listenagain (a_mode, a_url, a_filename): "Add raw links before listen again player links" fout = sys.stdout if a_filename != "-": fout = open (a_filename, 'w') if mode_is_list (a_mode): fout.write ("\n") fout.write (tag ("h1", a_url)) fout.write ("

\n") f = urllib.urlopen (a_url) for a_line in f.readlines(): r = bbc_player_raw_links (a_url, a_line) if r: if mode_is_list (a_mode): fout.write (tag ("li", a_link (r[1], r[0]) + " " + a_link (r[2], None))) else: fout.write (a_link (r[1], None) + " " + a_link (r[2], None)) fout.write (textify_img (absolute_href (a_url, a_line))) f.close() if mode_is_list (a_mode): fout.write ("\n") if fout != sys.stdout: fout.close() def usage (): print "usage: listenagain.py [list|patch] " print " list : raw list or http/ra URL in HTML format" print " patch : add URI inline in source page" print " in_url : input URL from which URL are extracted" print " out_html: output html file (- for stdout)" def mode_is_list (a): "Is the mode set to list" return a == "list" def usage_is_mode (a): "Is this a know mode?" return mode_is_list (a) or a == "patch" default_in_url = "http://www.bbc.co.uk/radio4/progs/listenagain.shtml" if __name__ == "__main__": "Comand line" out_html = "-" if len(sys.argv) >= 4: out_html = sys.argv[3] in_url = default_in_url if len(sys.argv) >= 3 and sys.argv[2] != "": in_url = sys.argv[2] if len(sys.argv) >= 2: if usage_is_mode (sys.argv[1]): mode = sys.argv[1] print "Converting to " + mode + " " + in_url process_listenagain (mode, in_url, out_html) else: # resolve stand alone player link print retrieve_realaudio_target (retrieve_bbc_realaudio (sys.argv[1])) else: usage ()