Created
November 12, 2013 11:16
-
-
Save krishnakummar/7429310 to your computer and use it in GitHub Desktop.
Create a html page to display all the profile images from ssmatri.com. This is for easy viewing. Its boring to click on each and every profile to view their details.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import requests | |
import BeautifulSoup | |
fo = open("ossmat.html", "wb") | |
session = requests.session() | |
for page in range(1,10): | |
req = session.get('http://ssmatri.net/setup/ProfileListview.asp?type=GI&sh=1&thisPage='+ str(page)) | |
doc = BeautifulSoup.BeautifulSoup(req.content) | |
all_td = doc.findAll('tr') | |
#for x in range(10,20): | |
starting_row = all_td[11] | |
ending_row = all_td[61] | |
all_href = starting_row.findAll('a') | |
for x in range(11,111): | |
if(x%2 != 0): | |
data = all_td[x] | |
all_links = data.findAll('a') | |
if(len(all_links) == 3): | |
href_link = 'http://ssmatri.net/setup/'+all_links[1]['href'] | |
profile_link = session.get(href_link) | |
profile_data = BeautifulSoup.BeautifulSoup(profile_link.content) | |
profile_data = profile_data.findAll('table') | |
name = "<BR>" + profile_data[1].find('font',{'color':'#009933'}).string + "<BR>" | |
fo.write("<a target='_blank' href='"+ href_link + "'>" + name + "</a>") | |
images = profile_data[1].findAll('img') | |
for image in images: | |
if(image['src'] != 'images/bot.gif'): | |
image_url = 'http://ssmatri.net/'+ image['src'].replace('../','') | |
fo.write("<img src=" + image_url + " />") | |
fo.write("<hr>") | |
fo.close() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment