fix: log the page being scraped

feat: delay option
This commit is contained in:
Mahdi Dibaiee 2017-04-19 22:14:54 +04:30
parent c73772addf
commit b0273c0cc3

View File

@ -7,6 +7,7 @@ import argparse
from urllib.parse import urlparse, urljoin from urllib.parse import urlparse, urljoin
from csv import DictWriter from csv import DictWriter
from helpers import to_absolute from helpers import to_absolute
import time
tags = ['p', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'ul', 'li', 'span', 'a', 'img'] tags = ['p', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'ul', 'li', 'span', 'a', 'img']
@ -14,6 +15,7 @@ parser = argparse.ArgumentParser(description='Web scraper')
parser.add_argument('file', help='path to file containing target websites, one line for each') parser.add_argument('file', help='path to file containing target websites, one line for each')
parser.add_argument('--depth', type=int, help='how deep should the scraper follow links') parser.add_argument('--depth', type=int, help='how deep should the scraper follow links')
parser.add_argument('--no-image', help='do not download images', action='store_true') parser.add_argument('--no-image', help='do not download images', action='store_true')
parser.add_argument('--delay', help='delay between requests in seconds, use to avoid being treated as an attacker', type=float)
args = parser.parse_args() args = parser.parse_args()
@ -42,6 +44,8 @@ for host in sites:
if t in visited: return if t in visited: return
print(t)
html = requests.get(t).text html = requests.get(t).text
visited.append(t) visited.append(t)
@ -81,6 +85,8 @@ for host in sites:
for link in queue: for link in queue:
queue.remove(link) queue.remove(link)
if args.delay is not None:
time.sleep(args.delay)
scrape(link, depth=depth + 1) scrape(link, depth=depth + 1)
scrape(main) scrape(main)