import thread
from lxml import html
import requests
import thread
tocrawl = ["link","link"]
def print_def( threadName):
page = requests.get(crawling)
tree = html.fromstring(page.text)
text = tree.xpath('//item')
print text
f = open('myfile','a+')
f.write(str(text)+"/n")
f.close
try:
for crawling in tocrawl:
thread.start_new_thread( print_def, (crawling,) )
except:
print "Error: unable to start thread"
while 1:
pass
Friday 18 October 2013
Python code to crawl the web page
simple html with javascript validation
<html>
<script>
function validation()
{
//first name
var a = document.form.firstName.value;
if(a=="")
{
alert("Please Enter Your First Name");
document.form.firstName.focus();
return false;
}
if(!isNaN(a))
{
alert("Please Enter Only Characters");
document.form.firstName.select();
return false;
}
if ((a.length < 5) || (a.length > 15))
{
alert("Your Character must be 5 to 15 Character");
document.form.firstName.select();
return false;
}
//last name
var a = document.form.lastName.value;
if(a == "")
{
alert("Please Enter Your Last Name");
document.form.lastName.focus();
return false;
}
if(!isNaN(a))
{
alert("Please Enter Only Characters");
document.form.lastName.select();
return false;
}
//gender validation
if(document.form.gender.value == "-1")
{
alert( "Please provide your Gender!" );
return false;
}
//address
var c = document.form.address.value;
if(c == "")
{
alert("Please Enter Your Address");
document.form.lastName.focus();
return false;
}
//cell
var d = document.form.cell.value;
if(d == "")
{
alert("Please Enter Your cell num");
document.form.lastName.focus();
return false;
}
if(isNaN(d))
{
alert("Please Enter numbers not characters");
document.form.lastName.select();
return false;
}
if (d.length < 10)
{
alert("Plz enter correct cell number");
document.form.firstName.select();
return false;
}
//country
if(document.form.country.value == "-1")
{
alert( "Please select your Country!" );
return false;
}
}
</script>
<head>
</head>
<body>
<form name="form" method="post" onsubmit="return validation()">
<table width="100%" height="100%" bgcolor="#E0F8F7" align="center">
<tr>
<td colspan=3 ><font size=3 color=red><right><b>USER ADDITIONAL INFORMATION FORM</b></right>
</tr>
<tr>
<td width="30%">First Name:<br/></td>
<td><input type="text" size=25 maxlength=20 name="firstName"></td>
</tr>
<tr>
<td width="30%">Last Name:<br/></td>
<td><input type="text" size=25 maxlength=20 name="lastName"></td>
</tr>
<tr>
<td width="30" valign="middle">Gender:</td>
<td><select name="gender">
<option value="-1" selected>---Select---</option>
<option value="1">Male</option>
<option value="2">Female</option>
</select>
</td>
</tr>
<tr>
<td width="30%">Adress:<br/></td>
<td><textarea rows=3 colos=30 name="address"></textarea></td>
</tr>
<tr>
<td width="30%">Cell no:<br/></td>
<td><input type="text" size=25 maxlength=10 name="cell"></td>
</tr>
<tr>
<td width="30" valign="middle">Select Country :</td>
<td><select name="country">
<option value="-1"selected>---Select---</option>
<option value="1">India</option>
<option value="2">Country</option>
<option value="3">Country</option>
<option value="4">Country</option>
<option value="5">Country</option>
<option value="6">Country</option>
</select></td>
</tr>
<tr>
<td ><input type="Reset">
<td ><input type="submit" value="Submit">
</tr>
</table>
</form>
</body>
</html>
Subscribe to:
Posts (Atom)