#!/usr/bin/env python
# coding: utf-8

# In[2]:


library(XML)
url="http://stats.espncricinfo.com/ci/engine/stats/index.html?class=1;team=8;template=results;type=batting"
#Note I can also break the url string and use paste command to modify this url with parameters
tables=readHTMLTable(url)
tables$"Overall figures"


# In[1]:


from bs4 import BeautifulSoup
import urllib


# In[16]:


r = urllib.urlopen("http://stats.espncricinfo.com/ci/engine/stats/index.html?class=1;team=8;template=results;type=batting").read()
soup = BeautifulSoup(r, "lxml")
headings=[row.get_text().encode("utf-8") for row in soup.find_all("th")]

datasets = []
for row in soup.find_all("tr"):
    
    data=[]
    for td in row.find_all("td"):
        data.append(td.get_text().encode("utf-8"))
    if len(data)==12:
        datasets.append(data)

    


# In[26]:


import numpy as np
import pandas as pd
table=pd.DataFrame(np.array(datasets),columns=headings)
print table


# In[ ]: