Differences

This shows you the differences between two versions of the page.

--- python:compare [2014/07/22 07:12] – [Match string with multilines] admin
+++ python:compare [2014/07/22 14:10] – [lxml.html.diff for comparing HTML files] admin
@@ Line 92: / Line 92: @@
 a[9] and b[9] match for 0 elements
 </code> **a[0] and b[4] match for 5 elements:** 5 elements from a[0] are ' abcd' and 5 elements from b[9] are ' abcd'
+=== get_opcodes ===
+<code python>
+import difflib
+import sys
+a = """ abcd
+abc pq
+ef abc
+mn
+""".splitlines(1)
+b = """abcd abcd
+ef
+mn
+""".splitlines(1)
+print 'a = ', a
+print 'b = ', b
+seq = difflib.SequenceMatcher(None, a, b)
+print '*******************************'
+for tag, alo, ahi, blo, bhi in seq.get_opcodes():
+    print '- ', tag, alo, ahi, blo, bhi, ':'
+    print '--from:'
+    for i in range(alo, ahi):
+        sys.stdout.writelines(a[i])
+    print '--to:'
+    for i in range(blo, bhi):
+        sys.stdout.writelines(b[i])
+result = list(difflib.ndiff(a, b))
+print '*******************************'
+print 'normal diff:'
+sys.stdout.writelines(result)
+</code>output:<code>
+a =  [' abcd\n', 'abc pq\n', 'ef abc\n', 'mn\n']
+b =  ['abcd abcd\n', 'ef\n', 'mn\n']
+*******************************
+-  replace 0 3 0 2 :
+--from:
+ abcd
+abc pq
+ef abc
+--to:
+abcd abcd
+ef
+-  equal 3 4 2 3 :
+--from:
+mn
+--to:
+mn
+*******************************
+normal diff:
+-  abcd
++ abcd abcd
+? ++++
++ ef
+- abc pq
+- ef abc
+  mn
+</code>
 === Match string with multilines ===
 <code python>
@@ Line 314: / Line 371: @@
   * etree for parsing HTML
 Examples for lxml.html.diff:
-  * Simple diff HTML:<code python>
+  * Simple diff:<code python>
+from os import path
+import sys, re
+from lxml.html import diff, etree, HTMLParser
+import codecs
+import StringIO
+doc1 = '''<div class="cart-button">
+<div class="cart">
+    <a title="Add to cart" data-id="35;" class="button addToCart-1 ">
+        <span>Add to cart</span>
+    </a>
+</div>
+<div class="wishlist">
+    <a class="tooltip-1" title="Add to Wish List" onclick="addToWishList('35');">
+    <i class="icon-star"></i>
+    <span>Add to Wish List</span>
+    </a>
+    <b>simple</b>
+</div>
+</div>'''
+doc2 = '''<div class="cart-button">
+<div class="cart">
+    <a title="Add to cart" data-id="35;" class="button addToCart-1 ">
+        <span>Add to cart</span>
+    </a>
+</div>
+<div class="wishlist">
+    <a class="tooltip-1" title="Add to Wish List" onclick="addToWishList('30');">
+    <i class="icon-star"></i>
+    <span>Add to Wish List change</span>
+    </a>
+</div>
+</div>'''
+diffcontent = diff.htmldiff(doc1, doc2)
+diffcontent = codecs.encode(diffcontent, 'utf-8')
+print diffcontent
+</code>output:<code html>
+<div class="cart-button"><div class="cart"><a title="Add to cart" data-id="35;" class="button addToCart-1 "><span>Add to cart</span> </a> </div> <div class="wishlist"><a class="tooltip-1" title="Add to Wish List" onclick="addToWishList('30');"><i class="icon-star"></i> <span>Add to Wish List <ins>change</ins> </span> </a> <del><b>simple</b></del> </div> </div>
+</code>
+  * diff 2 HTML files:<code python>
 from os import path
 import sys, re