Last active
June 20, 2020 17:18
-
-
Save KTibow/f7a5fd39f8a7fe0126b049486a6e20f3 to your computer and use it in GitHub Desktop.
Web crawler in Python with Regex!
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Libs | |
import re | |
from urllib.request import urlopen | |
from urllib.parse import urlparse | |
yoursite = "https://www.google.com/" | |
crawllist = [{"url": yoursite, "crawled": False}] | |
undecodable = [] | |
depth = 5 | |
for i in range(depth): | |
nlist = [] | |
for url in crawllist: | |
if url not in nlist: | |
nlist.append(url) | |
crawllist = nlist | |
# Message + copy list | |
print("Depth", i, "/", depth) | |
cwr = crawllist.copy() | |
# Go through sites | |
for i, url in enumerate(cwr): | |
# Check if not crawled and message | |
if not url["crawled"]: | |
print("Crawling " + url["url"]) | |
try: | |
# Download and parse | |
resy = urlopen(url["url"]).read().decode() | |
links = list(set(re.findall(r"(?i)(?::|src|href|background)(?: ?=)? ?\"(?:http|https)?(?::\/\/" + | |
urlparse(yoursite).netloc.replace(".", "\.") + | |
")?(\/?[\w\d\/\.]{2}[\w\d\/\.]{0,50})\"", | |
resy))) | |
for j, l in enumerate(links): | |
# Go through links and test | |
try: | |
ressy = urlopen(url["url"] + l) | |
if {"url": url["url"] + l, "crawled": False} not in crawllist: | |
toCrawl = False | |
try: | |
ressy.read().decode() | |
toCrawl = True | |
except UnicodeDecodeError: | |
undecodable.append(url["url"] + l) | |
crawllist.append({"url": url["url"] + l, "crawled": not toCrawl}) | |
print("======== Found " + url["url"] + l + " in " + url["url"]) | |
except Exception as e: | |
try: | |
ressy = urlopen(url["url"] + "/" + l) | |
if {"url": url["url"] + "/" + l, "crawled": False} not in crawllist: | |
toCrawl = False | |
try: | |
ressy.read().decode() | |
toCrawl = True | |
except UnicodeDecodeError: | |
undecodable.append(url["url"] + "/" + l) | |
crawllist.append({"url": url["url"] + "/" + l, "crawled": not toCrawl}) | |
print("======== Found " + url["url"] + "/" + l + " in " + url["url"] + "/") | |
except Exception as e: | |
try: | |
baseurl = "/".join(url["url"].split("/")[0: len(url["url"].split("/")) - 1]) | |
ressy = urlopen(baseurl + "/" + l) | |
if {"url": baseurl + "/" + l, "crawled": False} not in crawllist: | |
toCrawl = False | |
try: | |
ressy.read().decode() | |
toCrawl = True | |
except UnicodeDecodeError: | |
undecodable.append(baseurl + "/" + l) | |
crawllist.append({"url": baseurl + "/" + l, "crawled": not toCrawl}) | |
print("======== Found " + baseurl + "/" + l + " in " + baseurl + "/") | |
except Exception as e: | |
print("======== :/", l) | |
print("========[" + ((j + 1) * "#") + ((len(links)-j) * " ") + "]") | |
except UnicodeDecodeError: | |
print("UnicodeDecodeError") | |
except Exception as e: | |
print(e) | |
print("[" + ((i + 1) * "#") + ((len(cwr) - i) * " ") + "]") | |
url["crawled"] = True | |
urllist = [] | |
for url in crawllist: | |
if url["url"] not in urllist: | |
urllist.append(url["url"]) | |
print("URLs:") | |
for url in urllist: | |
print(url) | |
print("Undecodable:") | |
for url in list(set(undecodable)): | |
print(url) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment