Here is a small script I wrote to get the HNews ask section and display them without using a web browser. Just I'm just looking for feed backfeedback on how to improve my style/coding logic/overall code.
#!/usr/bin/python
'''This script gets the headlines from hacker news ask section'''
import urllib2
import HTMLParser
import re
class HNParser(HTMLParser.HTMLParser):
def __init__(self):
HTMLParser.HTMLParser.__init__(self)
self.data=[]
self.recording=0
def handle_starttag(self, tag, attribute):
if tag!='a':
return
elif self.recording:
self.recording +=1
return
for name, value in attribute:
if name=='href' and value[0]=='i':
break
else:
return
self.recording=1
def handle_endtag(self, tag):
if tag=='a' and self.recording:
self.recording-=1
def handle_data(self, data):
if self.recording:
self.data.append(data)
HOST='http://news.ycombinator.com/ask'
parser=HNParser()
f=urllib2.urlopen(HOST)
rawHTML=f.read()
parser.feed(rawHTML)
i=0
for items in parser.data:
try:
print parser.data[2*i]
i+=1
except IndexError:
break
parser.close()
Any comments would be great Thanks!
Here is a small script I wrote to get the HNews ask section and display them without using a web browser. Just looking for feed back on how to improve my style/coding logic/overall code.
#!/usr/bin/python
'''This script gets the headlines from hacker news ask section'''
import urllib2
import HTMLParser
import re
class HNParser(HTMLParser.HTMLParser):
def __init__(self):
HTMLParser.HTMLParser.__init__(self)
self.data=[]
self.recording=0
def handle_starttag(self, tag, attribute):
if tag!='a':
return
elif self.recording:
self.recording +=1
return
for name, value in attribute:
if name=='href' and value[0]=='i':
break
else:
return
self.recording=1
def handle_endtag(self, tag):
if tag=='a' and self.recording:
self.recording-=1
def handle_data(self, data):
if self.recording:
self.data.append(data)
HOST='http://news.ycombinator.com/ask'
parser=HNParser()
f=urllib2.urlopen(HOST)
rawHTML=f.read()
parser.feed(rawHTML)
i=0
for items in parser.data:
try:
print parser.data[2*i]
i+=1
except IndexError:
break
parser.close()
Any comments would be great Thanks!
Here is a small script I wrote to get the HNews ask section and display them without using a web browser. I'm just looking for feedback on how to improve my style/coding logic/overall code.
#!/usr/bin/python
'''This script gets the headlines from hacker news ask section'''
import urllib2
import HTMLParser
import re
class HNParser(HTMLParser.HTMLParser):
def __init__(self):
HTMLParser.HTMLParser.__init__(self)
self.data=[]
self.recording=0
def handle_starttag(self, tag, attribute):
if tag!='a':
return
elif self.recording:
self.recording +=1
return
for name, value in attribute:
if name=='href' and value[0]=='i':
break
else:
return
self.recording=1
def handle_endtag(self, tag):
if tag=='a' and self.recording:
self.recording-=1
def handle_data(self, data):
if self.recording:
self.data.append(data)
HOST='http://news.ycombinator.com/ask'
parser=HNParser()
f=urllib2.urlopen(HOST)
rawHTML=f.read()
parser.feed(rawHTML)
i=0
for items in parser.data:
try:
print parser.data[2*i]
i+=1
except IndexError:
break
parser.close()
Review my HNews "ask section" page scraping Python script to make it more pythonic
Loading
lang-py