lines: XML/HTML parsing

geekcomputers · Oct 5, 2020 · 67a65e3 · 67a65e3
1 parent ebfd55d
commit 67a65e3
Showing 1 changed file with 21 additions and 0 deletions.
diff --git a/XML/HTML parsing b/XML/HTML parsing
@@ -0,0 +1,21 @@
+dinner_recipe = '''<html><body><table>
+<tr><th>amt</th><th>unit</th><th>item</th></tr>
+<tr><td>24</td><td>slices</td><td>baguette</td></tr>
+<tr><td>2+</td><td>tbsp</td><td>olive oil</td></tr>
+<tr><td>1</td><td>cup</td><td>tomatoes</td></tr>
+<tr><td>1</td><td>jar</td><td>pesto</td></tr>
+</table></body></html>'''
+
+# From http://effbot.org/zone/element-index.htm
+import xml.etree.ElementTree as etree
+tree = etree.fromstring(dinner_recipe)
+
+# For invalid HTML use http://effbot.org/zone/element-soup.htm
+# import ElementSoup, StringIO
+# tree = ElementSoup.parse(StringIO.StringIO(dinner_recipe))
+
+pantry = set(['olive oil', 'pesto'])
+for ingredient in tree.getiterator('tr'):
+    amt, unit, item = ingredient
+    if item.tag == "td" and item.text not in pantry:
+        print ("%s: %s %s" % (item.text, amt.text, unit.text))