您应该使用一些HTML解析库，例如lxml：

from lxml import etree
s = """<table>
  <tr><th>Event</th><th>Start Date</th><th>End Date</th></tr>
  <tr><td>a</td><td>b</td><td>c</td></tr>
  <tr><td>d</td><td>e</td><td>f</td></tr>
  <tr><td>g</td><td>h</td><td>i</td></tr>
</table>
"""
table = etree.HTML(s).find("body/table")
rows = iter(table)
headers = [col.text for col in next(rows)]
for row in rows:
    values = [col.text for col in row]
    print dict(zip(headers, values))

版画

{'End Date': 'c', 'Start Date': 'b', 'Event': 'a'}
{'End Date': 'f', 'Start Date': 'e', 'Event': 'd'}
{'End Date': 'i', 'Start Date': 'h', 'Event': 'g'}