ImageMatik


Convert all TIFs in a directory to JPEGs
mogrify -format jpg -quality 50 *.tiff

http://linuxuser32.wordpress.com/2007/06/16/batch-image-convert-scale-thumbnail-jpegs-pdf/

Python: lxml insert element before and after given element

Python: lxml insert element before and after given element

Based on: http://stackoverflow.com/questions/7474972/python-lxml-append-element-after-another-element

from lxml import etree

xml = etree.parse('old_xml.xml')

count = 1

for pp in xml.xpath('/response/items/item'):

   prod_id = etree.Element('new_element')  # this element will be inserted

   prod_id.text = "%s" % count

   nav = pp.find('name')  # we will insert before/after this element

   div = nav.getparent()

   pp.insert(pp.index(nav), prod_id) # insert before 'name'

   pp.insert(pp.index(nav) + 1, prod_id) # insert after 'name'

   count += 1

out = open('new_xml.xml','w')

out.write(etree.tostring(xml, pretty_print=True))

out.close()

Python: Detect Charset and convert to Unicode


Converting data to Unicode via chardet 
http://stackoverflow.com/questions/2686709/encoding-in-python-with-lxml-complex-solution

import chardet
from lxml import html

f = open('my.xml')

content = f.read()

f.close()

encoding = chardet.detect(content)['encoding']
if encoding != 'utf-8':
    content = content.decode(encoding, 'replace').encode('utf-8')

Converting Data to Unicode via UnicodeDammit 

http://lxml.de/elementsoup.html

from BeautifulSoup import UnicodeDammit

converted = UnicodeDammit(content)

   if not converted.unicode: 

    raise UnicodeDecodeError( 

       "Failed to detect encoding, tried [%s]", 

        ', '.join(converted.triedEncodings))  

        # print converted.originalEncoding

         return converted.unicode

Credit goes to Ian Bicking and others on the lxml team

Using lxml xpath to get elements with a default namespace

xml_string="""

<a xmlns="http://www.w3.org/1999/xhtml">

  <b>
    <r>
      <Value>string</Value>

    </r>

    <r>

      <Value>string</Value>

    </r>

  </b>

  <e>

    <string>string1</string>

    <string>string2</string>

  </e>

</a>

"""

from lxml import etree

xml = etree.fromstring(xml_string)

xml.xpath('/w3:a/w3:b/w3:r/w3:Value/text()', namespaces={'w3':'http://www.w3.org/1999/xhtml'})