Reputation: 135
I am trying to make a web crawler using Python. I am borrowing this code from Programming Collective intelligence book by Toby Segaran. Since the code from the book was outdated, I made some necessary changes but still the program doesn't execute as expected. Here is my code:
import urllib
from urllib import request
from bs4 import BeautifulSoup
from urllib.parse import urljoin
import bs4
# Create a list of words to ignore
ignorewords=set(['the','of','to','and','a','in','is','it'])
class crawler:
# Initialize the crawler with the name of database
def __init__(self,dbname):
pass
def __del__(self): pass
def dbcommit(self):
pass
# Auxilliary function for getting an entry id and adding
# it if it's not present
def getentryid(self,table,field,value,createnew=True):
return None
# Index an individual page
def addtoindex(self,url,soup):
print('Indexing %s' % url)
# Extract the text from an HTML page (no tags)
def gettextonly(self,soup):
return None
# Separate the words by any non-whitespace character
def separatewords(self,text):
return None
# Return true if this url is already indexed
def isindexed(self,url):
return False
# Add a link between two pages
def addlinkref(self,urlFrom,urlTo,linkText):
pass
# Starting with a list of pages, do a breadth
# first search to the given depth, indexing pages
# as we go
def crawl(self,pages,depth=2):
pass
# Create the database tables
def createindextables(self):
pass
def crawl(self,pages,depth=2):
for i in range(depth):
newpages=set( )
for page in pages:
try:
c=request.urlopen(page)
except:
print("Could not open %s" % page)
continue
soup=BeautifulSoup(c.read())
self.addtoindex(page,soup)
links=soup('a')
for link in links:
if ('href' in dict(link.attrs)):
url=urljoin(page,link['href'])
if url.find("'")!=-1: continue
url=url.split('#')[0] # remove location portion
if url[0:4]=='http' and not self.isindexed(url):
newpages.add(url)
linkText=self.gettextonly(link)
self.addlinkref(page,url,linkText)
self.dbcommit( )
pages=newpages
pagelist=['http://google.com']
#pagelist=['file:///C:/Users/admin/Desktop/abcd.html']
crawler=crawler('')
crawler.crawl(pagelist)
the only output I get is "Indexing http://google.com" "Indexing http://google.com" press any key to continue...
Everytime I put another link in page list I get same output as "Indexing xyz" where xyz is every link I put in pagelist. I also tried making a HTML file with lots of <a>
tags but it didn't work too.
Upvotes: 2
Views: 273
Reputation: 598
The problem is in your line link=soup('a')
. If you want to find elements of class 'a', you should use the different methods named 'find_element_by...' (cf bs4 documentation)
Upvotes: 2