Scrape internal links with Beautiful soup - python

I have written a python code to fetch the web-page corresponding to a given url, and parses all the links on that page into a repository of links. Next, it fetches the contents of any of the url from the repository just created, parses the links from this new content into the repository and continues this process for all links in the repository until stopped or after a given number of links are fetched.
Here code:
import BeautifulSoup
import urllib2
import itertools
import random
class Crawler(object):
"""docstring for Crawler"""
def __init__(self):
self.soup = None # Beautiful Soup object
self.current_page = "http://www.python.org/" # Current page's address
self.links = set() # Queue with every links fetched
self.visited_links = set()
self.counter = 0 # Simple counter for debug purpose
def open(self):
# Open url
print self.counter , ":", self.current_page
res = urllib2.urlopen(self.current_page)
html_code = res.read()
self.visited_links.add(self.current_page)
# Fetch every links
self.soup = BeautifulSoup.BeautifulSoup(html_code)
page_links = []
try :
page_links = itertools.ifilter( # Only deal with absolute links
lambda href: 'http://' in href,
( a.get('href') for a in self.soup.findAll('a') ) )
except Exception: # Magnificent exception handling
pass
# Update links
self.links = self.links.union( set(page_links) )
# Choose a random url from non-visited set
self.current_page = random.sample( self.links.difference(self.visited_links),1)[0]
self.counter+=1
def run(self):
# Crawl 3 webpages (or stop if all url has been fetched)
while len(self.visited_links) < 3 or (self.visited_links == self.links):
self.open()
for link in self.links:
print link
if __name__ == '__main__':
C = Crawler()
C.run()
This code does not fetch internal links (only absolute formed hyperlinks)
How to fetch Internal links that starts with '/' or '#' or '.'

Well, your code kind of already tells you what's going on. In your lambda you are only grabbing absolute links that start with http:// (which you are not grabbing https FWIW). You should grab all of the links and check to see if they start with http+ or not. If they don't, then they are a relative link, and since you know what the current_page is then you can use that to create an absolute link.
Here's a modification to your code. Excuse my Python as it's a little rusty, but I ran it and it worked in Python 2.7 for me. You'll want to clean it up and add some edge/error detection, but you get the gist:
#!/usr/bin/python
from bs4 import BeautifulSoup
import urllib2
import itertools
import random
import urlparse
class Crawler(object):
"""docstring for Crawler"""
def __init__(self):
self.soup = None # Beautiful Soup object
self.current_page = "http://www.python.org/" # Current page's address
self.links = set() # Queue with every links fetched
self.visited_links = set()
self.counter = 0 # Simple counter for debug purpose
def open(self):
# Open url
print self.counter , ":", self.current_page
res = urllib2.urlopen(self.current_page)
html_code = res.read()
self.visited_links.add(self.current_page)
# Fetch every links
self.soup = BeautifulSoup(html_code)
page_links = []
try :
for link in [h.get('href') for h in self.soup.find_all('a')]:
print "Found link: '" + link + "'"
if link.startswith('http'):
page_links.append(link)
print "Adding link" + link + "\n"
elif link.startswith('/'):
parts = urlparse.urlparse(self.current_page)
page_links.append(parts.scheme + '://' + parts.netloc + link)
print "Adding link " + parts.scheme + '://' + parts.netloc + link + "\n"
else:
page_links.append(self.current_page+link)
print "Adding link " + self.current_page+link + "\n"
except Exception, ex: # Magnificent exception handling
print ex
# Update links
self.links = self.links.union( set(page_links) )
# Choose a random url from non-visited set
self.current_page = random.sample( self.links.difference(self.visited_links),1)[0]
self.counter+=1
def run(self):
# Crawl 3 webpages (or stop if all url has been fetched)
while len(self.visited_links) < 3 or (self.visited_links == self.links):
self.open()
for link in self.links:
print link
if __name__ == '__main__':
C = Crawler()
C.run()

chage condition in lambda:
page_links = itertools.ifilter( # Only deal with absolute links
lambda href: 'http://' in href or href.startswith('/') or href.startswith('#') or href.startswith('.'),
( a.get('href') for a in self.soup.findAll('a') ) )

Related

The python script is continuously running

I am trying to build a web crawler to extract all the links on a webpage. I have created 2 python files. (class: scanner.py and object: vulnerability-scanner.py). When I run the script, it is continuously running without stopping. I am unable to find the error. Help me to solve this.
Here is my source code:
scanner.py
import requests
from urllib.parse import urlparse, urljoin
from bs4 import BeautifulSoup
import colorama
class Scanner:
colorama.init()
def __init__(self, url):
self.target_url = url
self.target_links = []
def is_valid(self, url):
parsed = urlparse(url)
return bool(parsed.netloc) and bool(parsed.scheme)
def get_all_website_links(self, url):
GREEN = colorama.Fore.GREEN
WHITE = colorama.Fore.WHITE
RESET = colorama.Fore.RESET
urls = set()
internal_urls = set()
external_urls = set()
domain_name = urlparse(url).netloc
response = requests.get(url)
soup = BeautifulSoup(response.content, "html.parser")
for a_tag in soup.findAll("a"):
href = a_tag.attrs.get("href")
if href == "" or href is None:
continue
href = urljoin(url, href)
parsed_href = urlparse(href)
href = parsed_href.scheme + "://" + parsed_href.netloc + parsed_href.path
if not self.is_valid(href):
continue
if href in internal_urls:
continue
if domain_name not in href:
if href not in external_urls:
print(f"{WHITE}[*] External link: {href}{RESET}")
external_urls.add(href)
continue
print(f"{GREEN}[*] Internal link: {href}{RESET}")
urls.add(href)
internal_urls.add(href)
return urls
def crawl(self, url):
href_links = self.get_all_website_links(url)
for link in href_links:
print(link)
self.crawl(link)
vulnerability-scanner.py
import argu
target_url = "https://hack.me/"
vul_scanner = argu.Scanner(target_url)
vul_scanner.crawl(target_url)
The following part is (almost) an infinite recursion:
for link in href_links:
print(link)
self.crawl(link)
I believe you added this on the notion of crawling the links in the page. But you didn't put a stopping condition. (Although currently, it seems like your only stopping condition is if there is a crawled page with no links at all).
One stopping condition might be to set a predefined number of "max" levels to crawl.
Something like this in your init function:
def __init__(self, url):
self.target_url = url
self.target_links = []
self.max_parse_levels = 5 #you can go a step further and make this as an input to the constructore (i.e. __init__ function)
self.cur_parse_levels = 0
.
.
.
def crawl(url):
if self.cur_parse_levels > self.max_parse_levels:
return
for link in href_links:
print(link)
self.crawl(link)

Getting all links of a websites

Hi I wanted to create a mini crawler but not use Scrapy,
I created something like this:
response = requests.get(url)
homepage_link_list = []
soup = BeautifulSoup(response.content, 'lxml')
for link in soup.findAll("a"):
if link.get("href"):
homepage_link_list.append(link.get("href"))
link_list = []
for item in homepage_link_list:
response = requests.get(item)
soup = BeautifulSoup(response.content, 'lxml')
for link in soup.findAll("a"):
if link.get("href"):
link_list.append(link.get("href"))
Although the problem I am encountering is that it only get the the link within the link of webpage, how can I make it do get all the links within all the links of website.
You need a recursive call flow. I have written below a class-oriented code. Main points are as follows:
This implementation is depth-first
Keep track of already scraped URLs so that we don't scrape them again
Ignore targets on a page. Eg. if http://example.com#item1, ignore item1
If https://example.com is already crawled, ignore http://example.com
Discard trailing slash. Eg. if http://example.com is already crawled, ignore http://example.com/
''' Scraper.
'''
import re
from urllib.parse import urljoin, urlsplit, SplitResult
import requests
from bs4 import BeautifulSoup
class RecursiveScraper:
''' Scrape URLs in a recursive manner.
'''
def __init__(self, url):
''' Constructor to initialize domain name and main URL.
'''
self.domain = urlsplit(url).netloc
self.mainurl = url
self.urls = set()
def preprocess_url(self, referrer, url):
''' Clean and filter URLs before scraping.
'''
if not url:
return None
fields = urlsplit(urljoin(referrer, url))._asdict() # convert to absolute URLs and split
fields['path'] = re.sub(r'/$', '', fields['path']) # remove trailing /
fields['fragment'] = '' # remove targets within a page
fields = SplitResult(**fields)
if fields.netloc == self.domain:
# Scrape pages of current domain only
if fields.scheme == 'http':
httpurl = cleanurl = fields.geturl()
httpsurl = httpurl.replace('http:', 'https:', 1)
else:
httpsurl = cleanurl = fields.geturl()
httpurl = httpsurl.replace('https:', 'http:', 1)
if httpurl not in self.urls and httpsurl not in self.urls:
# Return URL only if it's not already in list
return cleanurl
return None
def scrape(self, url=None):
''' Scrape the URL and its outward links in a depth-first order.
If URL argument is None, start from main page.
'''
if url is None:
url = self.mainurl
print("Scraping {:s} ...".format(url))
self.urls.add(url)
response = requests.get(url)
soup = BeautifulSoup(response.content, 'lxml')
for link in soup.findAll("a"):
childurl = self.preprocess_url(url, link.get("href"))
if childurl:
self.scrape(childurl)
if __name__ == '__main__':
rscraper = RecursiveScraper("http://bbc.com")
rscraper.scrape()
print(rscraper.urls)
It could be that the links you want to scrape are not actually links. They could be images. Sorry for writing this answer here actally I dont have much reputation to comment,
Your code is not fetching all the links of the website because it is not recursive​. You're fetching the homepage links and traversing the links available in the content of the homepage links. But, you're not traversing the links you get in the content of those links you just traversed. My advice is you should check out some tree traversal algorithms and develop a scheme of traversal (recursive) according to the algorithm. The nodes of the trees will represent the links, root node being the link you passed in the beginning.
95% based on #coder.in.me answer let me insert another code here that can resolve an issue I was facing with.
My issue was: "If you try to scrape a url like: https://www.americanexpress.com/hu-hu/, it will only keep the https://www.americanexpress.com/ part of it and scrape all the amex sites globally, but I don't need all the non-hungarian pages."
You just need to change the
if fields.netloc == self.domain:
code to
if fields.netloc == self.domain and (fields.path.startswith('/hu-hu') or fields.path.startswith('/en-hu')):
Here is the modified code:
import re
from urllib.parse import urljoin, urlsplit, SplitResult
import requests
from bs4 import BeautifulSoup
class RecursiveScraper:
''' Scrape URLs in a recursive manner.
'''
def __init__(self, url):
''' Constructor to initialize domain name and main URL.
'''
self.domain = urlsplit(url).netloc
self.mainurl = url
self.urls = set()
def preprocess_url(self, referrer, url):
''' Clean and filter URLs before scraping.
'''
if not url:
return None
fields = urlsplit(urljoin(referrer, url))._asdict() # convert to absolute URLs and split
fields['path'] = re.sub(r'/$', '', fields['path']) # remove trailing /
fields['fragment'] = '' # remove targets within a page
fields = SplitResult(**fields)
#if fields.netloc == self.domain:
if fields.netloc == self.domain and (fields.path.startswith('/hu-hu') or fields.path.startswith('/en-hu')):
# Scrape pages of current domain only
if fields.scheme == 'http':
httpurl = cleanurl = fields.geturl()
httpsurl = httpurl.replace('http:', 'https:', 1)
else:
httpsurl = cleanurl = fields.geturl()
httpurl = httpsurl.replace('https:', 'http:', 1)
if httpurl not in self.urls and httpsurl not in self.urls:
# Return URL only if it's not already in list
return cleanurl
return None
def scrape(self, url=None):
''' Scrape the URL and its outward links in a depth-first order.
If URL argument is None, start from main page.
'''
if url is None:
url = self.mainurl
print("Scraping {:s} ...".format(url))
try:
response = requests.get(url)
self.urls.add(url)
soup = BeautifulSoup(response.content, 'lxml')
for link in soup.findAll("a"):
childurl = self.preprocess_url(url, link.get("href"))
if childurl:
self.scrape(childurl)
except requests.exceptions.SSLError:
pass
except requests.exceptions.InvalidSchema:
pass
if __name__ == '__main__':
rscraper = RecursiveScraper('https://www.americanexpress.com/hu-hu/')
rscraper.scrape()
Thanks!

How to obtain all the links in a domain using Python?

I want to use Python to obtain all the links in a domain given the 'root' URL (in a list). Suppose given a URL http://www.example.com this should return all the links on this page of the same domain as the root URL, then recurse on each of these links visiting them and extracting all the links of the same domain and so on. What I mean by same domain is if given http://www.example.com the only links I want back are http://www.example.com/something, http://www.example.com/somethingelse ... Anything external such as http://www.otherwebsite.com should be discarded. How can I do this using Python?
EDIT: I made an attempt using lxml. I don't think this works fully, and I am not sure how to take into account links to already processed pages (causing infinite loop).
import urllib
import lxml.html
#given a url returns list of all sublinks within the same domain
def getLinks(url):
urlList = []
urlList.append(url)
sublinks = getSubLinks(url)
for link in sublinks:
absolute = url+'/'+link
urlList.extend(getLinks(absolute))
return urlList
#determine whether two links are within the same domain
def sameDomain(url, dom):
return url.startswith(dom)
#get tree of sublinks in same domain, url is root
def getSubLinks(url):
sublinks = []
connection = urllib.urlopen(url)
dom = lxml.html.fromstring(connection.read())
for link in dom.xpath('//a/#href'):
if not (link.startswith('#') or link.startswith('http') or link.startswith('mailto:')):
sublinks.append(link)
return sublinks
~
import sys
import requests
import hashlib
from bs4 import BeautifulSoup
from datetime import datetime
def get_soup(link):
"""
Return the BeautifulSoup object for input link
"""
request_object = requests.get(link, auth=('user', 'pass'))
soup = BeautifulSoup(request_object.content)
return soup
def get_status_code(link):
"""
Return the error code for any url
param: link
"""
try:
error_code = requests.get(link).status_code
except requests.exceptions.ConnectionError:
error_code =
return error_code
def find_internal_urls(lufthansa_url, depth=0, max_depth=2):
all_urls_info = []
status_dict = {}
soup = get_soup(lufthansa_url)
a_tags = soup.findAll("a", href=True)
if depth > max_depth:
return {}
else:
for a_tag in a_tags:
if "http" not in a_tag["href"] and "/" in a_tag["href"]:
url = "http://www.lufthansa.com" + a_tag['href']
elif "http" in a_tag["href"]:
url = a_tag["href"]
else:
continue
status_dict["url"] = url
status_dict["status_code"] = get_status_code(url)
status_dict["timestamp"] = datetime.now()
status_dict["depth"] = depth + 1
all_urls_info.append(status_dict)
return all_urls_info
if __name__ == "__main__":
depth = 2 # suppose
all_page_urls = find_internal_urls("someurl", 2, 2)
if depth > 1:
for status_dict in all_page_urls:
find_internal_urls(status_dict['url'])
The above snippet contains necessary modules for scrapping urls from lufthansa arlines website. The only thing additional here is you can specify depth to which you want to scrape recursively.
Here is what I've done, only following full urls like http://domain[xxx]. Quick but a bit dirty.
import requests
import re
domain = u"stackoverflow.com"
http_re = re.compile(u"(http:\/\/" + domain + "[\/\w \.-]*\/?)")
visited = set([])
def visit (url):
visited.add (url)
extracted_body = requests.get (url).text
matches = re.findall (http_re, extracted_body)
for match in matches:
if match not in visited :
visit (match)
visit(u"http://" + domain)
print (visited)
There are some bugs in the code of #namita . I modify it and it works well now.
import sys
import requests
import hashlib
from bs4 import BeautifulSoup
from datetime import datetime
def get_soup(link):
"""
Return the BeautifulSoup object for input link
"""
request_object = requests.get(link, auth=('user', 'pass'))
soup = BeautifulSoup(request_object.content, "lxml")
return soup
def get_status_code(link):
"""
Return the error code for any url
param: link
"""
try:
error_code = requests.get(link).status_code
except requests.exceptions.ConnectionError:
error_code = -1
return error_code
def find_internal_urls(main_url, depth=0, max_depth=2):
all_urls_info = []
soup = get_soup(main_url)
a_tags = soup.findAll("a", href=True)
if main_url.endswith("/"):
domain = main_url
else:
domain = "/".join(main_url.split("/")[:-1])
print(domain)
if depth > max_depth:
return {}
else:
for a_tag in a_tags:
if "http://" not in a_tag["href"] and "https://" not in a_tag["href"] and "/" in a_tag["href"]:
url = domain + a_tag['href']
elif "http://" in a_tag["href"] or "https://" in a_tag["href"]:
url = a_tag["href"]
else:
continue
# print(url)
status_dict = {}
status_dict["url"] = url
status_dict["status_code"] = get_status_code(url)
status_dict["timestamp"] = datetime.now()
status_dict["depth"] = depth + 1
all_urls_info.append(status_dict)
return all_urls_info
if __name__ == "__main__":
url = # your domain here
depth = 1
all_page_urls = find_internal_urls(url, 0, 2)
# print("\n\n",all_page_urls)
if depth > 1:
for status_dict in all_page_urls:
find_internal_urls(status_dict['url'])
The code worked, but I don't know if it's 100% correct
it is extracting all the internal urls in the website
import requests
from bs4 import BeautifulSoup
def get_soup(link):
"""
Return the BeautifulSoup object for input link
"""
request_object = requests.get(link, auth=('user', 'pass'))
soup = BeautifulSoup(request_object.content, "lxml")
return soup
visited = set([])
def visit (url,domain):
visited.add (url)
soup = get_soup(url)
a_tags = soup.findAll("a", href=True)
for a_tag in a_tags:
if "http://" not in a_tag["href"] and "https://" not in a_tag["href"] and "/" in a_tag["href"]:
url = domain + a_tag['href']
elif "http://" in a_tag["href"] or "https://" in a_tag["href"]:
url = a_tag["href"]
else:
continue
if url not in visited and domain in url:
# print(url)
visit (url,domain)
url=input("Url: ")
domain=input("domain: ")
visit(u"" + url,domain)
print (visited)
From the tags of your question, I assume you are using Beautiful Soup.
At first, you obviously need to download the webpage, for example with urllib.request. After you did that and have the contents in a string, you pass it to Beautiful Soup. After that, you can find all links with soup.find_all('a'), assuming soup is your beautiful soup object. After that, you simply need to check the hrefs:
The most simple version would be to just check if "http://www.example.com" is in the href, but that won't catch relative links. I guess some wild regular expression would do (find everything with "www.example.com" or starting with "/" or starting with "?" (php)), or you might look for everything that contains a www, but is not www.example.com and discard it, etc. The correct strategy might be depending on the website you are scraping, and it's coding style.
You can use regular expression to filter out such links
eg
<a\shref\=\"(http\:\/\/example\.com[^\"]*)\"
Take the above regex as reference and start writing script based on that.

How to collect data of Google Search with beautiful soup using python

I want to know about how I can collect all the URL's and from the page source using beautiful soup and can visit all of them one by one in the google search results and move to next google index pages.
here is the URL https://www.google.com/search?q=site%3Awww.rashmi.com&rct=j that I want to collect and screen shot here http://www.rashmi.com/blog/wp-content/uploads/2014/11/screencapture-www-google-com-search-1433026719960.png
here is the code I'm trying
def getPageLinks(page):
links = []
for link in page.find_all('a'):
url = link.get('href')
if url:
if 'www.rashmi.com/' in url:
links.append(url)
return links
def Links(url):
pUrl = urlparse(url)
return parse_qs(pUrl.query)[0]
def PagesVisit(browser, printInfo):
pageIndex = 1
visited = []
time.sleep(5)
while True:
browser.get("https://www.google.com/search?q=site:www.rashmi.com&ei=50hqVdCqJozEogS7uoKADg" + str(pageIndex)+"&start=10&sa=N")
pList = []
count = 0
pageIndex += 1
Try this it should work.
def getPageLinks(page):
links = []
for link in page.find_all('a'):
url = link.get('href')
if url:
if 'www.rashmi.com/' in url:
links.append(url)
return links
def Links(url):
pUrl = urlparse(url)
return parse_qs(pUrl.query)
def PagesVisit(browser, printInfo):
start = 0
visited = []
time.sleep(5)
while True:
browser.get("https://www.google.com/search?q=site:www.rashmi.com&ei=V896VdiLEcPmUsK7gdAH&" + str(start) + "&sa=N")
pList = []
count = 0
# Random sleep to make sure everything loads
time.sleep(random.randint(1, 5))
page = BeautifulSoup(browser.page_source)
start +=10
if start ==500:
browser.close()

File Storage Problem with Python Web Crawler

I am screen scraping data using a web crawler and storing the results - (tweets from a twitter page) as separate html files for each user I'm crawling. I intend to later parse the html files and store the data into a database for analysis. However, I am having a bizarre problem.
When I run the following program - a small snippet from the overall crawler - I am able to get a separate html file for each follower:
import re
import urllib2
import twitter
start_follower = "NYTimesKrugman"
depth = 3
searched = set()
api = twitter.Api()
def crawl(follower, in_depth):
if in_depth > 0:
searched.add(follower)
directory = "C:\\Python28\\Followertest1\\" + follower + ".html"
output = open(directory, 'a')
output.write(follower)
output.write('\n\n')
users = api.GetFriends(follower)
names = set([str(u.screen_name) for u in users])
names -= searched
for name in list(names)[0:5]:
crawl(name, in_depth-1)
crawl(start_follower, depth)
for x in searched:
print x
print "Program is completed."
However, when I run the full crawler, I do not get a separate file for each follower:
import twitter
import urllib
from BeautifulSoup import BeautifulSoup
import re
import time
start_follower = "NYTimeskrugman"
depth = 2
searched = set()
api = twitter.Api()
def add_to_U(user):
U.append(user)
def site(follower): #creates a twitter site url in string format based on the follower username
followersite = "http://mobile.twitter.com/" + follower
return followersite
def getPage(follower): #obtains access to a webapge
url = site(follower)
response = urllib.urlopen(url)
return response
def getSoup(response): #creates the parsing module
html = response.read()
soup = BeautifulSoup(html)
return soup
def gettweets(soup, output):
tags = soup.findAll('div', {'class' : "list-tweet"})#to obtain tweet of a follower
for tag in tags:
a = tag.renderContents()
b = str (a)
output.write(b)
output.write('\n\n')
def are_more_tweets(soup):#to check whether there is more than one page on mobile twitter
links = soup.findAll('a', {'href': True}, {id: 'more_link'})
for link in links:
b = link.renderContents()
test_b = str(b)
if test_b.find('more') != -1:
return True
return False
def getnewlink(soup): #to get the link to go to the next page of tweets on twitter
links = soup.findAll('a', {'href': True}, {id : 'more_link'})
for link in links:
b = link.renderContents()
if str(b) == 'more':
c = link['href']
d = 'http://mobile.twitter.com' +c
return d
def crawl(follower, in_depth): #main method of sorts
if in_depth > 0:
searched.add(follower)
directory = "C:\\Python28\\Followertest2\\" + follower + ".html"
output = open(directory, 'a')
output.write(follower)
output.write('\n\n')
a = getPage(follower)
soup = getSoup(a)
gettweets(soup, output)
tweets = are_more_tweets(soup)
while(tweets):
b = getnewlink(soup)
red = urllib.urlopen(b)
html = red.read()
soup = BeautifulSoup(html)
gettweets(soup, output)
tweets = are_more_tweets(soup)
users = api.GetFriends(follower)
names = set([str(u.screen_name) for u in users])
names -= searched
for name in list(names)[0:5]:
print name
crawl(name, in_depth - 1)
crawl(start_follower, depth)
print("Program done. Look at output file.")
More specifically, I seem to get a separate html file for about the first five followers and then no new files appear to be created. Any help would be appreciated!
The depth value is different between the snippet and the full code (you're only going to get one level of recursion in the full code). Also, you only grab the first five names from the followers list: for name in list(names)[0:5]: So you get six people total: the starting follower and their first five friends.

Categories