Get pdftoxml working.

1 files changed, 22 insertions, 2 deletions

diff --git a/testlib/scraperwiki.py b/testlib/scraperwiki.py
index 901acec..0d7466e 100644
--- a/testlib/scraperwiki.py
+++ b/testlib/scraperwiki.py
@@ -1,4 +1,9 @@
+# The real version is available from
+# https://bitbucket.org/ScraperWiki/scraperwiki/src/85cbc82c32f2/scraperlibs/python/scraperwiki/
+
+import tempfile
 import urllib2
+import os
 
 def scrape(url):
     print "Scraping %s" % url
@@ -12,8 +17,23 @@ def scrape(url):
         html = response.read()
         return html
 
-def pdftoxml(pdfcontent, options):
-    return pdfcontent
+def pdftoxml(pdfdata, options=''):
+    """converts pdf file to xml file"""
+    pdffout = tempfile.NamedTemporaryFile(suffix='.pdf')
+    pdffout.write(pdfdata)
+    pdffout.flush()
+
+    xmlin = tempfile.NamedTemporaryFile(mode='r', suffix='.xml')
+    tmpxml = xmlin.name # "temph.xml"
+    cmd = '/usr/bin/pdftohtml -xml -nodrm -zoom 1.5 -enc UTF-8 -noframes %s "%s" "%s"' % (options, pdffout.name, os.path.splitext(tmpxml)[0])
+    cmd = cmd + " >/dev/null 2>&1" # can't turn off output, so throw away even stderr yeuch
+    os.system(cmd)
+
+    pdffout.close()
+    #xmlfin = open(tmpxml)
+    xmldata = xmlin.read()
+    xmlin.close()
+    return xmldata
 
 def swimport(scrapername):
     return None