Joe 7:22 pm on June 1, 2021
Tags: lxml, python ( 45 )

lxml insights

posted again because WordPress is BBBBBaddddd! at posting code!

I GIVE UP!!! I needto find someplace else to post code!

I am VERY SAD!

# "wordpress.com" "posting source code" "2021"  - Google Search
#   https://wordpress.com/tag/programming
# wordpress.com >> editor >> Block >> [HTML, HTML]
import sys, lxml.html, lxml.cssselect

# For more insights see [The lxml.etree Tutorial](https://lxml.de/tutorial.html)

def main():
    htmltree = lxml.html.fromstring(html_fragment)   
    # type(htmltree) => lxml.html.HtmlElement

    # There is no element.text() function     INSTEAD   lxml.html.tostring(element)
    print(lxml.html.tostring(htmltree))  # =>  b'<div><div class="chart_header">\n ...'
    
    # lxml Converts the tree   ===>   to lists of lists
    # [Elements are lists](lxml.de/tutorial.html#elements-are-lists)
    print(len(htmltree))       # 3
    print(len(htmltree[0]))    # 3
    print(len(htmltree[1]))    # 4
    print(len(htmltree[1][0])) # 0

    print(lxml.html.tostring(htmltree[1][0])) # b'<div class="chart_tabletitle1">CPU</div>    '
    print(lxml.html.tostring(htmltree[1][1])) # b'<div class="chart_tabletitle2">CPU Value (Mark/Price)</div>    '
    print(lxml.html.tostring(htmltree[1][2])) # b'<div class="chart_tabletitle4">CPU Mark</div>    '
    print(lxml.html.tostring(htmltree[1][3])) # b'<div class="chart_tabletitle3">Price (USD)</div>  '
    

    # [Elements carry attributes as a dict](https://lxml.de/tutorial.html#elements-carry-attributes-as-a-dict)
    print(htmltree[1][2].attrib['class'])  # chart_tabletitle4
    print(htmltree[1][3].attrib['class'])  # chart_tabletitle3




html_fragment = '''
<!-- at about line 2030 in view-source:https://www.cpubenchmark.net/high_end_cpus.html -->

  <div class="chart_header">
    <div class="chart_title">PassMark - CPU Mark</div>
    <div class="chart_subtitle">High End CPUs</div>
    <div class="chart_subtitle" style="font-size: small;">Updated 31st of May 2021</div>
  </div>
  <div class="chart_subheader">
    <div class="chart_tabletitle1">CPU</div>    <div class="chart_tabletitle2">CPU Value (Mark/Price)</div>    <div class="chart_tabletitle4">CPU Mark</div>    <div class="chart_tabletitle3">Price (USD)</div>  </div>
  <div class="chart_body">
    <ul class="chartlist">
<li id="pk4207"><span class="more_details" onclick="p(event, '87,767', 1, 12, 64, 2, 'NA');"><a class="name" href="cpu.php?cpu=AMD+EPYC+7763&amp;id=4207"></a></span><a href="cpu.php?cpu=AMD+EPYC+7763&amp;id=4207"><span class="prdname">AMD EPYC 7763</span><div><span class="index pink" style="width: 0%">(0%)</span></div><span class="count">NA</span><span class="mark-neww">87,767</span><span class="price-neww">NA</span></a></li>
<li id="pk3837"><span class="more_details" onclick="p(event, '86,096', 2, 19, 64, 2, '$5,489.99');"><a class="name" href="cpu.php?cpu=AMD+Ryzen+Threadripper+PRO+3995WX&amp;id=3837"></a></span><a href="cpu.php?cpu=AMD+Ryzen+Threadripper+PRO+3995WX&amp;id=3837"><span class="prdname">AMD Ryzen Threadripper PRO 3995WX</span><div><span class="index yellow" style="width: 46.5%">(46.5%)</span></div><span class="count">15.7</span><span class="mark-neww">86,096</span><span class="price-neww">$5,489.99</span></a></li>
<li id="pk4206"><span class="more_details" onclick="p(event, '85,887', 3, 16, 64, 2, 'NA');"><a class="name" href="cpu.php?cpu=AMD+EPYC+7713&amp;id=4206"></a></span><a href="cpu.php?cpu=AMD+EPYC+7713&amp;id=4206"><span class="prdname">AMD EPYC 7713</span><div><span class="index green" style="width: 0%">(0%)</span></div><span class="count">NA</span><span class="mark-neww">85,887</span><span class="price-neww">NA</span></a></li>
<li id="pk3674"><span class="more_details" onclick="p(event, '81,206', 4, 112, 64, 2, '$5,729.00*');"><a class="name" href="cpu.php?cpu=AMD+Ryzen+Threadripper+3990X&amp;id=3674"></a></span><a href="cpu.php?cpu=AMD+Ryzen+Threadripper+3990X&amp;id=3674"><span class="prdname">AMD Ryzen Threadripper 3990X</span><div><span class="index light-purple" style="width: 44.8%">(44.8%)</span></div><span class="count">14.2</span><span class="mark-neww">81,206</span><span class="price-neww">$5,729.00*</span></a></li>
<li id="pk4205"><span class="more_details" onclick="p(event, '77,101', 5, 3, 48, 2, 'NA');"><a class="name" href="cpu.php?cpu=AMD+EPYC+7643&amp;id=4205"></a></span><a href="cpu.php?cpu=AMD+EPYC+7643&amp;id=4205"><span class="prdname">AMD EPYC 7643</span><div><span class="index red" style="width: 0%">(0%)</span></div><span class="count">NA</span><span class="mark-neww">77,101</span><span class="price-neww">NA</span></a></li>
<li id="pk3719"><span class="more_details" onclick="p(event, '71,686', 6, 14, 64, 2, '$8,499.00');"><a class="name" href="cpu.php?cpu=AMD+EPYC+7702&amp;id=3719"></a></span><a href="cpu.php?cpu=AMD+EPYC+7702&amp;id=3719"><span class="prdname">AMD EPYC 7702</span><div><span class="index turquoise" style="width: 36.0%">(36.0%)</span></div><span class="count">8.4</span><span class="mark-neww">71,686</span><span class="price-neww">$8,499.00</span></a></li>
<li id="pk3555"><span class="more_details" onclick="p(event, '68,213', 7, 2, 64, 2, '$4,650.00*');"><a class="name" href="cpu.php?cpu=AMD+EPYC+7702P&amp;id=3555"></a></span><a href="cpu.php?cpu=AMD+EPYC+7702P&amp;id=3555"><span class="prdname">AMD EPYC 7702P</span><div><span class="index orange" style="width: 45.4%">(45.4%)</span></div><span class="count">14.7</span><span class="mark-neww">68,213</span><span class="price-neww">$4,650.00*</span></a></li>
</ul>
'''
if __name__ == '__main__':
    main()

#lxml, #python

Joe 7:18 pm on March 10, 2015
Tags: HTML ( 2 ), lxml, screen-scraping ( 3 )

lxml.html basic parse methods for [url, file, string]

lxml.html examples of parsing from

URLs
Files
Strings

URLs

import lxml.html
htmltree = lxml.html.parse('http://joecodeswell.com')

htmltree.xpath("//title")[0].text

'''
OUTPUT:
'JoeCodeswell.com'
'''

Files

N.B. Save ‘http://joecodeswell.com’ as a file named ‘JoeCodeswell.com.htm’.
Make sure to cd to the dir containing the file before running the following.

import lxml.html
htmltree = lxml.html.parse('JoeCodeswell.com.htm')

htmltree.xpath("//title")[0].text

'''
OUTPUT:
'JoeCodeswell.com'
'''

Strings

N.B. Save ‘http://joecodeswell.com’ as a file named ‘JoeCodeswell.com.htm’.
Make sure to cd to the dir containing the file before running the following.

import lxml.html

f = open('JoeCodeswell.com.htm', 'r'); the_string = f.read(); f.close()
htmltree = lxml.html.fromstring(the_string)

htmltree.xpath("//title")[0].text

'''
OUTPUT:
'JoeCodeswell.com'
'''

#html, #lxml, #screen-scraping

Joe 8:56 pm on January 21, 2015
Tags: lxml, screen-sxraping

More lxml Syntax Examples

Continued from lxml HTML Scraping Syntax Examples

Content:

Python Code
Resulting Output

Python Code

#!/usr/local/bin/python2.7
# -*- coding: UTF-8 -*-
"""lxmlScrapingExamplesMore.py takes INURL [URL to an html file] Producing OUTFILEPATH [a scrapped text file]
Usage:   lxmlScrapingExamplesMore.py INURL                                                  OUTFILEPATH
Example: lxmlScrapingExamplesMore.py http://joecodeswell.org/examples/dlwebfiles/acl_attach.htm lxmlScrapingOutput.txt
"""
import sys,os

# joe professional opinion: package structure a bit goofy!   🙂
import lxml, lxml.html


def lxmlScrapingExamples(myinurl, myoutfilepath):
    myinurl = 'http://joecodeswell.org/examples/dlwebfiles/acl_attach.htm' # what gets called
    print myinurl
    print myoutfilepath

    #Example 1 redo for myinurl new value 
    print "\n\nExample 1 - basic parsing of url"
    htmltree = lxml.html.parse(myinurl)
    # print "lxml.etree.tostring(htmltree, pretty_print=True) = %s"%(lxml.etree.tostring(htmltree, pretty_print=True))

    #Example 5 - xpath tag with class=value     N.B. backslashes for newLines, etc., DISAPPEAR in WordPress Marldown
    # see http://lxml.de/xpathxslt.html
    print "\n\nExample 5 - xpath tag with class=value"
    print """htmltree.xpath("//h1[@class='title topictitle1']")[0].text = %s"""%(htmltree.xpath("//h1[@class='title topictitle1']")[0].text)
    print """htmltree.xpath("//p[@class='shortdesc']")[0].text = %s"""%(htmltree.xpath("//p[@class='shortdesc']")[0].text)     
    print """len(htmltree.xpath("//var[@class='keyword varname']")) = %s"""%(len(htmltree.xpath("//var[@class='keyword varname']")))
    print """htmltree.xpath("//var[@class='keyword varname']")[0].text = %s"""%(htmltree.xpath("//var[@class='keyword varname']")[0].text)

    #Example 6 - parent   and   ElementVariables with   //  VS  .//   
    print "\n\nExample 6 - parent and ElementVariables"
    print """syntax_div = htmltree.xpath("//h2[@class='title sectiontitle']")[0].getparent() = %s"""%(htmltree.xpath("//h2[@class='title sectiontitle']")[0].getparent())
    syntax_div = htmltree.xpath("//h2[@class='title sectiontitle']")[0].getparent()
    print """syntax_div = %s"""%(syntax_div)
    print syntax_div_2string,'\n'
    print """syntax_div = %s"""%(syntax_div)  

    print "\n\nsyntax_div.xpath     //   VS  .//  \n\n"   
    print "// uses  htmltree"
    print """    syntax_div.xpath("count(//samp)") = %s"""%(syntax_div.xpath("count(//samp)"))  
    print '            equals\n'
    print """    htmltree.xpath("count(//samp)") = %s"""%(htmltree.xpath("count(//samp)"))  
    print """    syntax_div.xpath("count(//var)") = %s"""%(syntax_div.xpath("count(//var)"))  
    print '            equals'
    print """    htmltree.xpath("count(//var)") = %s"""%(htmltree.xpath("count(//var)"))  
    print '\nVS   .// uses  syntax_div ONLY'
    print """    htmltree.xpath("count(.//samp)") = %s"""%(htmltree.xpath("count(.//samp)"))  
    print """    syntax_div.xpath("count(.//var)") = %s"""%(syntax_div.xpath("count(.//var)")) 
    print "\n"    
    print syntax_div_ipython_discovery

    #Example 7 - xpath select element by text
    print "\n\nExample 7 - xpath select element by text"
    print """description_div = htmltree.xpath("//h2[@class='title sectiontitle' and text()='Description']")[0].getparent() = %s"""%(htmltree.xpath("//h2[@class='title sectiontitle' and text()='Description']")[0].getparent())
    description_div = htmltree.xpath("//h2[@class='title sectiontitle' and text()='Description']")[0].getparent()
    print """description_div = %s"""%(description_div)
    print description_div_2string,'\n'
    print """description_div.xpath("./p")[0].text = %s"""%(description_div.xpath("./p")[0].text)


    #Example 8 - get all text in an element
    print "\n\nExample 8 - get all text in element\nsee http://lxml.de/lxmlhtml.html#html-element-methods"
    print """xample_div = htmltree.xpath("//h2[@class='title sectiontitle' and text()='Example']")[0].getparent() = %s"""%(htmltree.xpath("//h2[@class='title sectiontitle' and text()='Example']")[0].getparent())    
    example_div = htmltree.xpath("//h2[@class='title sectiontitle' and text()='Example']")[0].getparent()
    print example_div_2string,'\n'
    print "example_div.text_content() = %s"%(example_div.text_content())


    #Example 9 - zip/dict   data terms & data definitions
    print "\n\nExample 9 - zipping data terms & data definitions"
    print """options_div = htmltree.xpath("//h2[@class='title sectiontitle' and text()='Options']")[0].getparent() = %s"""%(htmltree.xpath("//h2[@class='title sectiontitle' and text()='Options']")[0].getparent())    
    options_div = htmltree.xpath("//h2[@class='title sectiontitle' and text()='Options']")[0].getparent()
    print options_div_2string
    terms = [t.text for t in options_div.xpath("dl/dt/samp/var")]
    defs  = [d.text for d in options_div.xpath("dl/dd")]
    term_def_dict = dict(zip(terms, defs))
    print '\nterm_def_dict'
    for k, v in term_def_dict.iteritems():
        print '    %s: %s'%(k,v)


#print lxml.etree.tostring(options_div, pretty_print=True)

options_div_2string = """<div class="section">
  <h2 class="title sectiontitle">Options</h2>
  <dl class="dl">
    <dt class="dt dlterm">
      <samp class="ph codeph">
        <var class="keyword varname">acl_name</var>
      </samp>
    </dt>
    <dd class="dd">Specifies the ACL policy that is applied to the named object.
      The ACL policy must exist, or an error is displayed. 
      <p class="p">Examples of
      the ACL names are 
        <samp class="ph codeph">default-root</samp>, 
        <samp class="ph codeph">test</samp>, 
        <samp class="ph codeph">default-management</samp>,
        and 
        <samp class="ph codeph">pubs_acl3</samp>.</p>
    </dd>
    <dt class="dt dlterm">
      <samp class="ph codeph">
        <var class="keyword varname">object_name</var>
      </samp>
    </dt>
    <dd class="dd">Specifies the object to which to apply the named ACL policy. The
    object name must exist, or an error is displayed. 
      <p class="p">Examples of object
      names are:
      </p>
      <ul class="ul">
        <li class="li">
          <samp class="ph codeph">/Management/Groups/Travel</samp>
        </li>
        <li class="li">
          <samp class="ph codeph">/WebSEAL</samp>
        </li>
        <li class="li">
          <samp class="ph codeph">/Management</samp>
        </li>
      </ul>
    </dd>
  </dl>
</div>"""



example_div_2string = """<div class="example">
  <h2 class="title sectiontitle">Example</h2>
  <div class="p">The following example attaches the ACL policy, 
    <samp class="ph codeph">pubs_acl3</samp>, 
    to the protected object, 
    <samp class="ph codeph">/Management</samp>: 
    <pre class="pre codeblock">
      <code>pdadmin sec_master> acl attach /Management pubs_acl3</code>
    </pre>
  </div>
</div>
"""    

description_div_2string = """<div class="section">
  <h2 class="title sectiontitle">Syntax</h2>
  <p class="p">
    <span class="keyword cmdname">acl attach</span>
    <samp class="ph codeph">
      <var class="keyword varname">object_name</var></samp> 
    <samp class="ph codeph">
      <var class="keyword varname">acl_name</var>
    </samp>
  </p>
 </div>"""

syntax_div_2string = """<div class="section">
  <h2 class="title sectiontitle">Syntax</h2>
  <p class="p">
    <span class="keyword cmdname">acl attach</span> 
    <samp class="ph codeph">
      <var class="keyword varname">object_name</var>
    </samp> 
    <samp class="ph codeph">
      <var class="keyword varname">acl_name</var>
    </samp>
  </p>
 </div>"""

syntax_div_ipython_discovery = """In [54]: syntax_div.
syntax_div.addnext             syntax_div.get_element_by_id   syntax_div.keys
syntax_div.addprevious         syntax_div.getchildren         syntax_div.label
syntax_div.append              syntax_div.getiterator         syntax_div.make_links_absolut
syntax_div.attrib              syntax_div.getnext             syntax_div.makeelement
syntax_div.base                syntax_div.getparent           syntax_div.nsmap
syntax_div.base_url            syntax_div.getprevious         syntax_div.prefix
syntax_div.body                syntax_div.getroottree         syntax_div.remove
syntax_div.clear               syntax_div.head                syntax_div.replace
syntax_div.cssselect           syntax_div.index               syntax_div.resolve_base_href
syntax_div.drop_tag            syntax_div.insert              syntax_div.rewrite_links
syntax_div.drop_tree           syntax_div.items               syntax_div.set
syntax_div.extend              syntax_div.iter                syntax_div.sourceline
syntax_div.find                syntax_div.iterancestors       syntax_div.tag
syntax_div.find_class          syntax_div.iterchildren        syntax_div.tail
syntax_div.find_rel_links      syntax_div.iterdescendants     syntax_div.text
syntax_div.findall             syntax_div.iterfind            syntax_div.text_content
syntax_div.findtext            syntax_div.iterlinks           syntax_div.values
syntax_div.forms               syntax_div.itersiblings        syntax_div.xpath
syntax_div.get                 syntax_div.itertext
"""

NUM_ARGS = 2
def main():
    args = sys.argv[1:]
    if len(args) != NUM_ARGS or "-h" in args or "--help" in args:
        print __doc__
        s = raw_input('hit return to quit')
        sys.exit(2)
    lxmlScrapingExamples(args[0], args[1])

if __name__ == '__main__':
    main()

Resulting Output

>lxmlScrapingExamplesMore.py http://joecodeswell.org/examples/dlwebfiles/acl_attach.htm lxmlScrapingOutput.txt
http://joecodeswell.org/examples/dlwebfiles/acl_attach.htm
lxmlScrapingOutput.txt


Example 1 - basic parsing of url


Example 5 - xpath tag with class=value
htmltree.xpath("//h1[@class='title topictitle1']")[0].text = acl attach
htmltree.xpath("//p[@class='shortdesc']")[0].text = Attaches an ACL policy to a protected object. If the protected
object already has an ACL attached, the ACL is replaced with a new
one. 
len(htmltree.xpath("//var[@class='keyword varname']")) = 4
htmltree.xpath("//var[@class='keyword varname']")[0].text = object_name


Example 6 - parent and ElementVariables
syntax_div = htmltree.xpath("//h2[@class='title sectiontitle']")[0].getparent() = <Element div at 0xb7df00>
syntax_div = <Element div at 0xb7df00>
<div class="section">
  <h2 class="title sectiontitle">Syntax</h2>
  <p class="p">
    <span class="keyword cmdname">acl attach</span> 
    <samp class="ph codeph">
      <var class="keyword varname">object_name</var>
    </samp> 
    <samp class="ph codeph">
      <var class="keyword varname">acl_name</var>
    </samp>
  </p>
 </div> 

syntax_div = <Element div at 0xb7df00>


syntax_div.xpath     //   VS  .//  


// uses  htmltree
    syntax_div.xpath("count(//samp)") = 14.0
            equals

    htmltree.xpath("count(//samp)") = 14.0
    syntax_div.xpath("count(//var)") = 4.0
            equals
    htmltree.xpath("count(//var)") = 4.0

VS   .// uses  syntax_div ONLY
    htmltree.xpath("count(.//samp)") = 14.0
    syntax_div.xpath("count(.//var)") = 2.0


In [54]: syntax_div.
syntax_div.addnext             syntax_div.get_element_by_id   syntax_div.keys
syntax_div.addprevious         syntax_div.getchildren         syntax_div.label
syntax_div.append              syntax_div.getiterator         syntax_div.make_links_absolut
syntax_div.attrib              syntax_div.getnext             syntax_div.makeelement
syntax_div.base                syntax_div.getparent           syntax_div.nsmap
syntax_div.base_url            syntax_div.getprevious         syntax_div.prefix
syntax_div.body                syntax_div.getroottree         syntax_div.remove
syntax_div.clear               syntax_div.head                syntax_div.replace
syntax_div.cssselect           syntax_div.index               syntax_div.resolve_base_href
syntax_div.drop_tag            syntax_div.insert              syntax_div.rewrite_links
syntax_div.drop_tree           syntax_div.items               syntax_div.set
syntax_div.extend              syntax_div.iter                syntax_div.sourceline
syntax_div.find                syntax_div.iterancestors       syntax_div.tag
syntax_div.find_class          syntax_div.iterchildren        syntax_div.tail
syntax_div.find_rel_links      syntax_div.iterdescendants     syntax_div.text
syntax_div.findall             syntax_div.iterfind            syntax_div.text_content
syntax_div.findtext            syntax_div.iterlinks           syntax_div.values
syntax_div.forms               syntax_div.itersiblings        syntax_div.xpath
syntax_div.get                 syntax_div.itertext



Example 7 - xpath select element by text
description_div = htmltree.xpath("//h2[@class='title sectiontitle' and text()='Description']")[0].getparent() = <Element div at 0xd10e40>
description_div = <Element div at 0xd10e40>
<div class="section">
  <h2 class="title sectiontitle">Syntax</h2>
  <p class="p">
    <span class="keyword cmdname">acl attach</span>
    <samp class="ph codeph">
      <var class="keyword varname">object_name</var></samp> 
    <samp class="ph codeph">
      <var class="keyword varname">acl_name</var>
    </samp>
  </p>
 </div> 

description_div.xpath("./p")[0].text = At most, one ACL can be attached
to a given protected object. The same ACL can be attached to multiple
protected objects. Ensure that you are familiar with ACL management before you
use this function.


Example 8 - get all text in element
see http://lxml.de/lxmlhtml.html#html-element-methods
xample_div = htmltree.xpath("//h2[@class='title sectiontitle' and text()='Example']")[0].getparent() = <Element div at 0xd10e70>
<div class="example">
  <h2 class="title sectiontitle">Example</h2>
  <div class="p">The following example attaches the ACL policy, 
    <samp class="ph codeph">pubs_acl3</samp>, 
    to the protected object, 
    <samp class="ph codeph">/Management</samp>: 
    <pre class="pre codeblock">
      <code>pdadmin sec_master> acl attach /Management pubs_acl3</code>
    </pre>
  </div>
</div>


example_div.text_content() = ExampleThe following example attaches the
ACL policy, pubs_acl3, to the protected object, /Management: pdadmin sec_master> acl attach /Management pubs_acl3




Example 9 - zipping data terms & data definitions
options_div = htmltree.xpath("//h2[@class='title sectiontitle' and text()='Options']")[0].getparent() = <Element div at 0xd10d80>
<div class="section">
  <h2 class="title sectiontitle">Options</h2>
  <dl class="dl">
    <dt class="dt dlterm">
      <samp class="ph codeph">
        <var class="keyword varname">acl_name</var>
      </samp>
    </dt>
    <dd class="dd">Specifies the ACL policy that is applied to the named object.
      The ACL policy must exist, or an error is displayed. 
      <p class="p">Examples of
      the ACL names are 
        <samp class="ph codeph">default-root</samp>, 
        <samp class="ph codeph">test</samp>, 
        <samp class="ph codeph">default-management</samp>,
        and 
        <samp class="ph codeph">pubs_acl3</samp>.</p>
    </dd>
    <dt class="dt dlterm">
      <samp class="ph codeph">
        <var class="keyword varname">object_name</var>
      </samp>
    </dt>
    <dd class="dd">Specifies the object to which to apply the named ACL policy. The
    object name must exist, or an error is displayed. 
      <p class="p">Examples of object
      names are:
      </p>
      <ul class="ul">
        <li class="li">
          <samp class="ph codeph">/Management/Groups/Travel</samp>
        </li>
        <li class="li">
          <samp class="ph codeph">/WebSEAL</samp>
        </li>
        <li class="li">
          <samp class="ph codeph">/Management</samp>
        </li>
      </ul>
    </dd>
  </dl>
</div>

term_def_dict
    object_name: Specifies the object to which to apply the named ACL policy. The
object name must exist, or an error is displayed. 
    acl_name: Specifies the ACL policy that is applied to the named object.
The ACL policy must exist, or an error is displayed. 

>

#lxml, #screen-sxraping

Joe 5:23 pm on January 19, 2015
Tags: HTML ( 2 ), lxml, python ( 45 ), screen-scraping ( 3 )

lxml HTML Scraping Syntax Examples

lxml Syntax Examples

Content:

Python Code
Resulting Output

Python Code

#!/usr/local/bin/python2.7
# -*- coding: UTF-8 -*-
"""lxmlScrapingExamples.py takes INURL [URL to an html file] Producing OUTFILEPATH [a scrapped text file]
Usage:   lxmlScrapingExamples.py INURL                                                  OUTFILEPATH
Example: lxmlScrapingExamples.py http://joecodeswell.org/examples/dlwebfiles/htmlExample.html lxmlScrapingOutput.txt
"""
import sys

# joe professional opinion: package structure a bit goofy!   🙂
import lxml, lxml.html


def lxmlScrapingExamples(myinurl, myoutfilepath):
    print myinurl
    print myoutfilepath

    #Example 1 - basic parsing of url - slightly altered from: http://stackoverflow.com/a/14303564/601770
    print "\n\nExample 1 - basic parsing of url"
    htmltree = lxml.html.parse(myinurl)
    print "lxml.etree.tostring(htmltree, pretty_print=True) = %s"%(lxml.etree.tostring(htmltree, pretty_print=True))



    #Example 2 - syntax examples [css_selector, xpath] - slightly altered from: http://stackoverflow.com/a/603630/601770
    print "\n\nExample 2 - syntax examples [css_selector, xpath]"
    # joe comment - i don't know why htmltree DOESN'T WORK DIRECTLY in this example it generates error:
    #     more lxml package/module/class/function assymetry?
    '''
    File "C:\1d\PythonPjs\kivyPjs\IBMsecurityAPIclientsPj\IBMsecurityAPIclient\ngExamples.py", line 28, in lxmlScrapingExamples
        for a in mySearchTree.cssselect('tr a'):
    AttributeError: 'lxml.etree._ElementTree' object has no attribute 'cssselect'    
    '''
    #mySearchTree = htmltree
    mySearchTree = lxml.html.fromstring(lxml.etree.tostring(htmltree))         
    # Find all 'a' elements inside 'tr' table rows with css selector
    print "Find all 'a' elements inside 'tr' table rows with css selector"
    for itm in mySearchTree.cssselect('tr a'):
        print 'found "%s" link to href "%s"' % (itm.text, itm.get('href'))    
    # Find all 'a' elements inside 'tr' table rows with xpath
    print "Find all 'a' elements inside 'tr' table rows with xpath"
    for itm in mySearchTree.xpath('.//tr/*/a'):
        print 'found "%s" link to href "%s"' % (itm.text, itm.get('href'))

    #Example 3 - syntax examples [xpath, .findall(), .getchildren()] - slightly altered from: http://stackoverflow.com/a/9920703/601770
    print "\n\nExample 3 - syntax examples [xpath, .findall(), .getchildren()] "
    page = htmltree
    rows = page.xpath("body/table")[1].findall("tr")   # table [1] is the 2nd table in MY example html
    data = list()
    for row in rows:
        data.append([c.text for c in row.getchildren()])
    for itm in data[4:]: print(itm)

    #Example 4 - following sibling [] - slightly altered from: http://stackoverflow.com/questions/3139402/how-to-select-following-sibling-xml-tag-using-xpath
    print "\n\nExample 4 - following sibling []"
    sibEx = '''
    <html>
    <head>
    <title>following sibling</title>
    </head>
    <body>
    <table border>    
    <tr>
        <td class="name">Brand</td>
        <td class="desc">Intel</td>
    </tr>
    <tr>
        <td class="name">Series</td>
        <td class="desc">Core i5</td>
    </tr>
    <tr>
        <td class="name">Cores</td>
        <td class="desc">4</td>
    </tr>
    <tr>
        <td class="name">Socket</td>
        <td class="desc">LGA 1156</td>    
    </tr>

    <tr>
        <td class="name">Brand</td>
        <td class="desc">AMD</td>
    </tr>
    <tr>
        <td class="name">Series</td>
        <td class="desc">Phenom II X4</td>
    </tr>
    <tr>
        <td class="name">Cores</td>
        <td class="desc">4</td>
    </tr>
    <tr>
        <td class="name">Socket</td>
        <td class="desc">Socket AM3</td>
    </tr>
    </table>
    </body>
    </html>    
    '''
    parsedDocument = lxml.html.fromstring(sibEx)

    # bad
    #rlist = parsedDocument.xpath("tr[td[@class='name'] ='Brand']")
    #rlist = parsedDocument.xpath("tr[td[@class='name'] ='Brand']/td[@class='desc']")
    #r = parsedDocument.xpath(tr/td[@class="name"])=='Brand')
    # r = parsedDocument.tr[td[@class='name'] ='Brand'].text
    #r = parsedDocument.tr[td[@class='name'] ='Brand']/td[@class='desc'].text
    #if(parsedDocument.xpath(tr/td[@class="name"])=='Brand'):

    # good
    #print "parsedDocument.xpath('/html/body/table/tr') = %s"%(parsedDocument.xpath('/html/body/table/tr'))
    print """parsedDocument.xpath("//tr[td[@class='name'] ='Brand']/td[@class='desc']") = %s"""%(parsedDocument.xpath("//tr[td[@class='name'] ='Brand']/td[@class='desc']"))
    print """parsedDocument.xpath("//tr[td[@class='name'] ='Brand']/td[@class='desc']")[0].text = %s"""%(parsedDocument.xpath("//tr[td[@class='name'] ='Brand']/td[@class='desc']")[0].text)



    print '\n\n\n'


NUM_ARGS = 2
def main():
    args = sys.argv[1:]
    if len(args) != NUM_ARGS or "-h" in args or "--help" in args:
        print __doc__
        s = raw_input('hit return to quit')
        sys.exit(2)
    lxmlScrapingExamples(args[0], args[1])

if __name__ == '__main__':
    main()

Resulting Output

>lxmlScrapingExamples.py http://joecodeswell.org/examples/dlwebfiles/htmlExample.html lxmlScrapingOutput.txt
http://joecodeswell.org/examples/dlwebfiles/htmlExample.html
lxmlScrapingOutput.txt


Example 1 - basic parsing of url
lxml.etree.tostring(htmltree, pretty_print=True) = <!DOCTYPE html>
<html>
  <head>
    <meta http-equiv="content-type" content="text/html; charset=windows-1252"/>
    <title>lxml htmlExamples.html</title>
  </head>
  <body>
    <h1>lxml htmlExamples.html for Joe Codeswell examples - dlwebfiles</h1>

    <h2>Example 1</h2>
    <ul><li><a href="http://joecodeswell.org/examples/dlwebfiles/aveverum.mid">aveverum.mid</a></li>
      <li><a href="http://joecodeswell.org/examples/dlwebfiles/carol.mid">carol.mid</a></li>
      <li><a href="http://joecodeswell.org/examples/dlwebfiles/steiner.mid">steiner.mid</a></li>
    </ul><h2>Example 2</h2>
    <table align="left" border="0" cellspacing="0" cellpadding="0" width="100%"><tr align="left" valign="top"><th>Name</th>
        <th>File Name & Link</th>
      </tr><tr align="left" valign="top"><td>Ave Verum</td><td><a href="http://joecodeswell.org/examples/dlwebfiles/aveverum.mid">aveverum.mid</a></td></tr><tr align="left" valign="top"><td>A Carol</td><td><a href="http://joecodeswell.org/examples/dlwebfiles/carol.mid.mid">carol.mid</a></td></tr><tr align="left" valign="top"><td>Steiner Amen?</td><td><a href="http://joecodeswell.org/examples/dlwebfiles/steiner.mid">steiner.mid</a></td></tr></table><h2>Example 3</h2>
    <table border=""><tr align="LEFT"><th colspan="38">Main Subject</th>
    </tr><tr align="LEFT"><th colspan="2"> </th>

    <th valign="TOP" colspan="18">part1</th>
    <th valign="TOP" colspan="18">part2</th>
    </tr><tr align="LEFT"><th colspan="2"> </th>
    <th valign="TOP" colspan="9">sub-part1</th>
    <th valign="TOP" colspan="9">sub-part2</th>
    <th valign="TOP" colspan="9">sub-part3</th>
    <th valign="TOP" colspan="9">sub-part4</th>
    </tr><tr align="LEFT"><th colspan="2"> </th>
    <th valign="TOP" colspan="1">subject1</th>
    <th valign="TOP" colspan="1">subject2</th>

    <th valign="TOP" colspan="1">subject10</th>
    <th valign="TOP" colspan="1">subject11</th>
    <th valign="TOP" colspan="1">subject12</th>
    <th valign="TOP" colspan="1">subject13</th>
    <th valign="TOP" colspan="1">subject14</th>
    <th valign="TOP" colspan="1">subject15</th>
    <th valign="TOP" colspan="1">subject16</th>

    <th valign="TOP" colspan="1">subject17</th>
    <th valign="TOP" colspan="1">subject18</th>
    <th valign="TOP" colspan="1">subject19</th>
    <th valign="TOP" colspan="1">subject20</th>
    <th valign="TOP" colspan="1">subject21</th>
    <th valign="TOP" colspan="1">subject22</th>
    <th valign="TOP" colspan="1">subject23</th>
    <th valign="TOP" colspan="1">subject24</th>
    <th valign="TOP" colspan="1">subject25</th>

    <th valign="TOP" colspan="1">subject26</th>
    <th valign="TOP" colspan="1">subject27</th>
    <th valign="TOP" colspan="1">subject28</th>
    <th valign="TOP" colspan="1">subject29</th>
    <th valign="TOP" colspan="1">subject30</th>
    <th valign="TOP" colspan="1">subject31</th>
    <th valign="TOP" colspan="1">subject32</th>
    <th valign="TOP" colspan="1">subject33</th>
    <th valign="TOP" colspan="1">subject34</th>

    <th valign="TOP" colspan="1">subject35</th>
    <th valign="TOP" colspan="1">subject36</th>
    </tr><tr align="RIGHT"><th align="LEFT" valign="TOP" rowspan="12">2050</th>
    <th align="LEFT">January</th>
    <td>0</td>
    <td>1</td>
    <td>3</td>
    <td>0</td>

    <td>4</td>
    <td>16</td>
    <td>0</td>
    <td>6</td>
    <td>2</td>
    <td>2</td>
    <td>0</td>
    <td>3</td>
    <td>0</td>

    <td>3</td>
    <td>2</td>
    <td>0</td>
    <td>26</td>
    <td>1</td>
    <td>0</td>
    <td>0</td>
    <td>7</td>
    <td>0</td>

    <td>5</td>
    <td>6</td>
    <td>0</td>
    <td>8</td>
    <td>2</td>
    <td>0</td>
    <td>0</td>
    <td>0</td>
    <td>0</td>

    <td>0</td>
    <td>0</td>
    <td>0</td>
    <td>2</td>
    <td>0</td>
    </tr><tr align="RIGHT"><th align="LEFT">February</th>
    <td>1</td>
    <td>0</td>

    <td>8</td>
    <td>0</td>
    <td>2</td>
    <td>4</td>
    <td>1</td>
    <td>6</td>
    <td>1</td>
    <td>2</td>
    <td>0</td>

    <td>3</td>
    <td>0</td>
    <td>0</td>
    <td>4</td>
    <td>0</td>
    <td>25</td>
    <td>0</td>
    <td>0</td>
    <td>1</td>

    <td>2</td>
    <td>0</td>
    <td>4</td>
    <td>14</td>
    <td>1</td>
    <td>1</td>
    <td>0</td>
    <td>0</td>
    <td>0</td>

    <td>0</td>
    <td>0</td>
    <td>0</td>
    <td>1</td>
    <td>0</td>
    <td>0</td>
    <td>0</td>
    </tr><tr align="RIGHT"><th align="LEFT">March</th>

    <td>0</td>
    <td>0</td>
    <td>4</td>
    <td>0</td>
    <td>4</td>
    <td>7</td>
    <td>0</td>
    <td>9</td>
    <td>2</td>

    <td>1</td>
    <td>0</td>
    <td>0</td>
    <td>0</td>
    <td>2</td>
    <td>9</td>
    <td>0</td>
    <td>45</td>
    <td>1</td>

    <td>0</td>
    <td>0</td>
    <td>7</td>
    <td>0</td>
    <td>10</td>
    <td>16</td>
    <td>0</td>
    <td>5</td>
    <td>1</td>

    <td>1</td>
    <td>0</td>
    <td>1</td>
    <td>0</td>
    <td>0</td>
    <td>0</td>
    <td>0</td>
    <td>4</td>
    <td>0</td>

    </tr><tr align="RIGHT"><th align="LEFT">April</th>
    <td>1</td>
    <td>0</td>
    <td>5</td>
    <td>0</td>
    <td>3</td>
    <td>12</td>
    <td>1</td>

    <td>11</td>
    <td>0</td>
    <td>3</td>
    <td>0</td>
    <td>3</td>
    <td>0</td>
    <td>0</td>
    <td>3</td>
    <td>2</td>

    <td>34</td>
    <td>0</td>
    <td>0</td>
    <td>1</td>
    <td>2</td>
    <td>0</td>
    <td>6</td>
    <td>18</td>
    <td>1</td>

    <td>3</td>
    <td>0</td>
    <td>0</td>
    <td>0</td>
    <td>0</td>
    <td>0</td>
    <td>0</td>
    <td>0</td>
    <td>0</td>

    <td>5</td>
    <td>1</td>
    </tr><tr align="RIGHT"><th align="LEFT">May</th>
    <td>7</td>
    <td>0</td>
    <td>6</td>
    <td>0</td>
    <td>8</td>

    <td>4</td>
    <td>1</td>
    <td>13</td>
    <td>0</td>
    <td>0</td>
    <td>2</td>
    <td>2</td>
    <td>0</td>
    <td>1</td>

    <td>7</td>
    <td>1</td>
    <td>30</td>
    <td>0</td>
    <td>0</td>
    <td>0</td>
    <td>7</td>
    <td>0</td>
    <td>5</td>

    <td>12</td>
    <td>0</td>
    <td>4</td>
    <td>1</td>
    <td>0</td>
    <td>0</td>
    <td>0</td>
    <td>0</td>
    <td>0</td>

    <td>0</td>
    <td>0</td>
    <td>6</td>
    <td>1</td>
    </tr><tr align="RIGHT"><th align="LEFT">June</th>
    <td>0</td>
    <td>1</td>
    <td>14</td>

    <td>0</td>
    <td>7</td>
    <td>15</td>
    <td>0</td>
    <td>17</td>
    <td>1</td>
    <td>2</td>
    <td>0</td>
    <td>5</td>

    <td>0</td>
    <td>1</td>
    <td>3</td>
    <td>0</td>
    <td>24</td>
    <td>0</td>
    <td>0</td>
    <td>0</td>
    <td>5</td>

    <td>0</td>
    <td>6</td>
    <td>13</td>
    <td>1</td>
    <td>9</td>
    <td>1</td>
    <td>1</td>
    <td>0</td>
    <td>0</td>

    <td>0</td>
    <td>0</td>
    <td>0</td>
    <td>0</td>
    <td>2</td>
    <td>1</td>
    </tr><tr align="RIGHT"><th align="LEFT">July</th>
    <td>0</td>

    <td>1</td>
    <td>6</td>
    <td>0</td>
    <td>8</td>
    <td>17</td>
    <td>1</td>
    <td>15</td>
    <td>2</td>
    <td>1</td>

    <td>0</td>
    <td>10</td>
    <td>0</td>
    <td>2</td>
    <td>15</td>
    <td>2</td>
    <td>53</td>
    <td>0</td>
    <td>3</td>

    <td>3</td>
    <td>6</td>
    <td>0</td>
    <td>7</td>
    <td>16</td>
    <td>0</td>
    <td>9</td>
    <td>1</td>
    <td>1</td>

    <td>0</td>
    <td>0</td>
    <td>0</td>
    <td>0</td>
    <td>1</td>
    <td>0</td>
    <td>2</td>
    <td>0</td>
    </tr><tr align="RIGHT"><th align="LEFT">August</th>
    <td>2</td>
    <td>0</td>
    <td>5</td>
    <td>0</td>
    <td>8</td>
    <td>15</td>
    <td>1</td>

    <td>17</td>
    <td>0</td>
    <td>2</td>
    <td>0</td>
    <td>2</td>
    <td>0</td>
    <td>5</td>
    <td>16</td>
    <td>0</td>

    <td>33</td>
    <td>0</td>
    <td>0</td>
    <td>0</td>
    <td>11</td>
    <td>0</td>
    <td>2</td>
    <td>25</td>
    <td>4</td>

    <td>8</td>
    <td>0</td>
    <td>0</td>
    <td>0</td>
    <td>1</td>
    <td>0</td>
    <td>0</td>
    <td>0</td>
    <td>0</td>

    <td>3</td>
    <td>0</td>
    </tr><tr align="RIGHT"><th align="LEFT">September</th>
    <td>2</td>
    <td>0</td>
    <td>10</td>
    <td>0</td>
    <td>16</td>

    <td>22</td>
    <td>2</td>
    <td>19</td>
    <td>4</td>
    <td>2</td>
    <td>0</td>
    <td>0</td>
    <td>0</td>
    <td>2</td>

    <td>8</td>
    <td>0</td>
    <td>27</td>
    <td>0</td>
    <td>1</td>
    <td>0</td>
    <td>8</td>
    <td>0</td>
    <td>11</td>

    <td>31</td>
    <td>1</td>
    <td>9</td>
    <td>0</td>
    <td>0</td>
    <td>0</td>
    <td>1</td>
    <td>0</td>
    <td>0</td>

    <td>0</td>
    <td>1</td>
    <td>1</td>
    <td>0</td>
    </tr><tr align="RIGHT"><th align="LEFT">October</th>
    <td>3</td>
    <td>1</td>
    <td>8</td>

    <td>0</td>
    <td>4</td>
    <td>28</td>
    <td>0</td>
    <td>15</td>
    <td>2</td>
    <td>1</td>
    <td>0</td>
    <td>1</td>

    <td>0</td>
    <td>1</td>
    <td>6</td>
    <td>0</td>
    <td>15</td>
    <td>0</td>
    <td>1</td>
    <td>0</td>
    <td>3</td>

    <td>0</td>
    <td>9</td>
    <td>26</td>
    <td>1</td>
    <td>8</td>
    <td>4</td>
    <td>0</td>
    <td>0</td>
    <td>0</td>

    <td>0</td>
    <td>0</td>
    <td>0</td>
    <td>0</td>
    <td>1</td>
    <td>0</td>
    </tr><tr align="RIGHT"><th align="LEFT">November</th>
    <td>0</td>

    <td>3</td>
    <td>3</td>
    <td>0</td>
    <td>6</td>
    <td>23</td>
    <td>1</td>
    <td>8</td>
    <td>1</td>
    <td>2</td>

    <td>0</td>
    <td>1</td>
    <td>0</td>
    <td>3</td>
    <td>7</td>
    <td>1</td>
    <td>20</td>
    <td>0</td>
    <td>0</td>

    <td>0</td>
    <td>8</td>
    <td>0</td>
    <td>3</td>
    <td>18</td>
    <td>3</td>
    <td>7</td>
    <td>0</td>
    <td>0</td>

    <td>0</td>
    <td>0</td>
    <td>0</td>
    <td>0</td>
    <td>0</td>
    <td>0</td>
    <td>3</td>
    <td>0</td>
    </tr><tr align="RIGHT"><th align="LEFT">December</th>
    <td>1</td>
    <td>0</td>
    <td>4</td>
    <td>0</td>
    <td>4</td>
    <td>13</td>
    <td>2</td>

    <td>15</td>
    <td>1</td>
    <td>0</td>
    <td>0</td>
    <td>2</td>
    <td>0</td>
    <td>1</td>
    <td>2</td>
    <td>0</td>

    <td>29</td>
    <td>0</td>
    <td>1</td>
    <td>0</td>
    <td>7</td>
    <td>0</td>
    <td>3</td>
    <td>20</td>
    <td>1</td>

    <td>13</td>
    <td>0</td>
    <td>1</td>
    <td>0</td>
    <td>0</td>
    <td>0</td>
    <td>0</td>
    <td>0</td>
    <td>0</td>

    <td>3</td>
    <td>0</td>
    </tr></table></body>
</html>



Example 2 - syntax examples [css_selector, xpath]
Find all 'a' elements inside 'tr' table rows with css selector
found "aveverum.mid" link to href "http://joecodeswell.org/examples/dlwebfiles/aveverum.mid"
found "carol.mid" link to href "http://joecodeswell.org/examples/dlwebfiles/carol.mid.mid"
found "steiner.mid" link to href "http://joecodeswell.org/examples/dlwebfiles/steiner.mid"
Find all 'a' elements inside 'tr' table rows with xpath
found "aveverum.mid" link to href "http://joecodeswell.org/examples/dlwebfiles/aveverum.mid"
found "carol.mid" link to href "http://joecodeswell.org/examples/dlwebfiles/carol.mid.mid"
found "steiner.mid" link to href "http://joecodeswell.org/examples/dlwebfiles/steiner.mid"


Example 3 - syntax examples [xpath, .findall(), .getchildren()] 
['2050', 'January', '0', '1', '3', '0', '4', '16', '0', '6', '2', '2', '0', '3', '0', '3', '2', '0', '26', '1', '0', '0', '7', '0', '5', '6', '0', '8', '2', '0', '0', '0', '0', '0', '0', '0', '2', '0']
['February', '1', '0', '8', '0', '2', '4', '1', '6', '1', '2', '0', '3', '0', '0', '4', '0', '25', '0', '0', '1', '2', '0', '4', '14', '1', '1', '0', '0', '0', '0', '0', '0', '1', '0', '0', '0']
['March', '0', '0', '4', '0', '4', '7', '0', '9', '2', '1', '0', '0', '0', '2', '9', '0', '45', '1', '0', '0', '7', '0', '10', '16', '0', '5', '1', '1', '0', '1', '0', '0', '0', '0', '4', '0']
['April', '1', '0', '5', '0', '3', '12', '1', '11', '0', '3', '0', '3', '0', '0', '3', '2', '34', '0', '0', '1', '2', '0', '6', '18', '1', '3', '0', '0', '0', '0', '0', '0', '0', '0', '5', '1']
['May', '7', '0', '6', '0', '8', '4', '1', '13', '0', '0', '2', '2', '0', '1', '7', '1', '30', '0', '0', '0', '7', '0', '5', '12', '0', '4', '1', '0', '0', '0', '0', '0', '0', '0', '6', '1']
['June', '0', '1', '14', '0', '7', '15', '0', '17', '1', '2', '0', '5', '0', '1', '3', '0', '24', '0', '0', '0', '5', '0', '6', '13', '1', '9', '1', '1', '0', '0', '0', '0', '0', '0', '2', '1']
['July', '0', '1', '6', '0', '8', '17', '1', '15', '2', '1', '0', '10', '0', '2', '15', '2', '53', '0', '3', '3', '6', '0', '7', '16', '0', '9', '1', '1', '0', '0', '0', '0', '1', '0', '2', '0']
['August', '2', '0', '5', '0', '8', '15', '1', '17', '0', '2', '0', '2', '0', '5', '16', '0', '33', '0', '0', '0', '11', '0', '2', '25', '4', '8', '0', '0', '0', '1', '0', '0', '0', '0', '3', '0']
['September', '2', '0', '10', '0', '16', '22', '2', '19', '4', '2', '0', '0', '0', '2', '8', '0', '27', '0', '1', '0', '8', '0', '11', '31', '1', '9', '0', '0', '0', '1', '0', '0', '0', '1', '1', '0']
['October', '3', '1', '8', '0', '4', '28', '0', '15', '2', '1', '0', '1', '0', '1', '6', '0', '15', '0', '1', '0', '3', '0', '9', '26', '1', '8', '4', '0', '0', '0', '0', '0', '0', '0', '1', '0']
['November', '0', '3', '3', '0', '6', '23', '1', '8', '1', '2', '0', '1', '0', '3', '7', '1', '20', '0', '0', '0', '8', '0', '3', '18', '3', '7', '0', '0', '0', '0', '0', '0', '0', '0', '3', '0']
['December', '1', '0', '4', '0', '4', '13', '2', '15', '1', '0', '0', '2', '0', '1', '2', '0', '29', '0', '1', '0', '7', '0', '3', '20', '1', '13', '0', '1', '0', '0', '0', '0', '0', '0', '3', '0']


Example 4 - following sibling []
parsedDocument.xpath("//tr[td[@class='name'] ='Brand']/td[@class='desc']") = [<Element td at 0xda53c0>, <Element td at 0xda5390>]
parsedDocument.xpath("//tr[td[@class='name'] ='Brand']/td[@class='desc']")[0].text = Intel

>

#html, #lxml, #python, #screen-scraping

Joe 2:55 pm on April 29, 2014
Tags: examples ( 9 ), lxml, python ( 45 ), screen-scraping ( 3 ), urllib

Scrape HTML Files with lxml

GREAT lxml example links

HTML Node vs Element

W3C HTML Nodes may be:

Document — Element (maximum of one), ProcessingInstruction, Comment, DocumentType
DocumentFragment — Element, ProcessingInstruction, Comment, Text, CDATASection, EntityReference
DocumentType — no children
EntityReference — Element, ProcessingInstruction, Comment, Text, CDATASection, EntityReference
Element — Element, Text, Comment, ProcessingInstruction, CDATASection, EntityReference
Attr — Text, EntityReference
ProcessingInstruction — no children
Comment — no children
Text — no children
CDATASection — no children
Entity — Element, ProcessingInstruction, Comment, Text, CDATASection, EntityReference
Notation — no children # My Scrape HTML File Example

Background

This, http://joecodeswell.org/examples/dlwebfiles/index.html, is the URL we will be scraping using lmxl, to find files to download, and using urllib to download them. Here is what the URL content looks like.

<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2 Final//EN">
<html>
  <head>
    <meta http-equiv="content-type" content="text/html; charset=windows-1252">
    <title>dlwebfiles</title>
  </head>
  <body>
    <h1>Index of Joe Codeswell examples - dlwebfiles</h1>
    <ul>
      <li><a href="http://joecodeswell.org/examples/dlwebfiles/aveverum.mid">aveverum.mid</a></li>
      <li><a href="http://joecodeswell.org/examples/dlwebfiles/carol.mid">carol.mid</a></li>
      <li><a href="http://joecodeswell.org/examples/dlwebfiles/steiner.mid">steiner.mid</a></li>
    </ul>
  </body>
</html>

Step-1

Create a folder structure on your local machine == “example_folder/mid".

Step-2

Put the following Python code into a file in example_folder, naming it “retrieveMidis.py“.

# -*- coding: UTF-8 -*-
# retrieveMidis.py

import os, lxml.html, urllib

inScrapeUrl = 'http://joecodeswell.org/examples/dlwebfiles/index.html'
outDataFolderPath = os.path.join('mid')

# parse the html
htmltree = lxml.html.parse(inScrapeUrl)

# retrieve the midi files to the ./mid dir
theLiList = htmltree.xpath('/html/body/ul/li')  
opener = urllib.URLopener()
for li in theLiList:
    # see http://www.w3schools.com/xpath/xpath_syntax.asp
    theHref = li.xpath('a')[0].attrib.get('href')
    theBasename = os.path.basename(theHref)
    theExtension = os.path.splitext(theBasename)[1]
    if len(theBasename) != 0:
        print "theHref = %s"%(theHref)
        print "theBasename = %s"%(theBasename)
        print "len(theBasename) = %s"%(len(theBasename))
        print "theExtension = %s"%(theExtension)
        print "os.path.join(outDataFolderPath,theBasenme) = %s"%(os.path.join(outDataFolderPath,theBasename))
        print
        print
        opener.retrieve(theHref, os.path.join(outDataFolderPath,theBasename))

Step-3

Run retrieveMidis.py.

Here’s what the output looks like on Win XP.

>retrieveMidis.py
theHref = http://joecodeswell.org/examples/dlwebfiles/aveverum.mid
theBasename = aveverum.mid
len(theBasename) = 12
theExtension = .mid
os.path.join(outDataFolderPath,theBasenme) = midaveverum.mid


theHref = http://joecodeswell.org/examples/dlwebfiles/carol.mid
theBasename = carol.mid
len(theBasename) = 9
theExtension = .mid
os.path.join(outDataFolderPath,theBasenme) = midcarol.mid


theHref = http://joecodeswell.org/examples/dlwebfiles/steiner.mid
theBasename = steiner.mid
len(theBasename) = 11
theExtension = .mid
os.path.join(outDataFolderPath,theBasenme) = midsteiner.mid

#examples, #lxml, #python, #screen-scraping, #urllib

Joe Codeswell – Notes to Myself and Others

Joe Dorocak's Programing Blog (We have a new look – Automatic's P2 Theme)

Tag Archives: lxml

lxml insights

lxml.html basic parse methods for [url, file, string]

lxml.html examples of parsing from

URLs

Files

Strings

More lxml Syntax Examples

More lxml Syntax Examples

Python Code

Resulting Output

lxml HTML Scraping Syntax Examples

lxml Syntax Examples

Python Code

Resulting Output

Scrape HTML Files with lxml

GREAT lxml example links

HTML Node vs Element

Background

Step-1

Step-2

Step-3