Last active
April 22, 2020 20:27
-
-
Save openroomxyz/32e3e820326ec59272a447cccc2b6f7d to your computer and use it in GitHub Desktop.
Python : How to get a list of all URLs on some domain crawling from page to page on that domain?
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
| import bs4 as bs | |
| import urllib.request | |
| import time | |
| def filter_to(input_list,limit_to): | |
| res = [] | |
| for i in input_list: | |
| if i is not None: | |
| if limit_to in i: | |
| res.append(i) | |
| return res | |
| visited = {} | |
| def Crawl(urls_list = ['https://www.x.si/'], limit_to = 'https://www.x.si/'): | |
| res = [] | |
| one_is_to_visit_for_sure = False | |
| for page in urls_list: | |
| if page not in visited: | |
| print("Visiting page : " + page) | |
| time.sleep(1) | |
| try: | |
| sauce = urllib.request.urlopen(page).read() | |
| soup = bs.BeautifulSoup(sauce, 'lxml') | |
| except: | |
| soup = False | |
| if soup != False: | |
| for url in soup.find_all('a'): | |
| new_url = url.get('href') | |
| if new_url not in visited: | |
| res.append(new_url) | |
| one_is_to_visit_for_sure = True | |
| visited[page] = True; | |
| res = filter_to(res, limit_to) | |
| if one_is_to_visit_for_sure: | |
| return Crawl(res, limit_to) | |
| return res | |
| print("----") | |
| resx = Crawl(limit_to = 'https://somedomain.xyz/') | |
| print("DONE") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment