iNocturnis/webcrawler
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

changed elif to if to speed up regex in is_vaild

Browse Source
This commit is contained in:
Lacerum 2022-04-20 12:18:25 -07:00
parent af26611ef4
commit ab39c4b8c6
1 changed files with 6 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
spacetime-crawler4py-master/scraper.py
View File

@ -139,24 +139,24 @@ def is_valid(url):
# https://support.archive-it.org/hc/en-us/articles/208332963-Modify-crawl-scope-with-a-Regular-Expression # https://support.archive-it.org/hc/en-us/articles/208332963-Modify-crawl-scope-with-a-Regular-Expression
# length check for looping filters and queries (could add hash check for similarity or regex, but don't know if we want to as this works well enought) # length check for looping filters and queries (could add hash check for similarity or regex, but don't know if we want to as this works well enought)
# we can adjust it based on what the cralwer does as well # we can adjust it based on what the cralwer does as well
elif len(url) > 169: if len(url) > 169:
return False return False
# this fixes any search box that keeps going page to page, currenty allow a depth of 2 filters # this fixes any search box that keeps going page to page, currenty allow a depth of 2 filters
elif re.match(r".*(&filter%.*){3,}",url_parsed_path): if re.match(r".*(&filter%.*){3,}",url_parsed_path):
return False return False
# this is for urls which when opened, download a file (do we want to download these files and tokenize them) # this is for urls which when opened, download a file (do we want to download these files and tokenize them)
# elif re.match(r"^.*\&format=(\D{3,4})\Z$",url_parsed_path): # elif re.match(r"^.*\&format=(\D{3,4})\Z$",url_parsed_path):
# return False # return False
# another looping directory check but more advanced than the one contained in is_a_trap # another looping directory check but more advanced than the one contained in is_a_trap
elif re.match(r"^.*?(/.+?/).*?\1.*$|^.*?/(.+?/)\2.*$",url_parsed_path): if re.match(r"^.*?(/.+?/).*?\1.*$|^.*?/(.+?/)\2.*$",url_parsed_path):
return False return False
# extra directories check (we can add as we find) # extra directories check (we can add as we find)
elif re.match(r"^.*(/misc|/sites|/all|/themes|/modules|/profiles|/css|/field|/node|/theme){3}.*$", url_parsed_path): if re.match(r"^.*(/misc|/sites|/all|/themes|/modules|/profiles|/css|/field|/node|/theme){3}.*$", url_parsed_path):
return False return False
# calendar checks plus adding or downloading calendar (ical) # calendar checks plus adding or downloading calendar (ical)
elif re.match(r"^.*calendar.*$",url_parsed_path): if re.match(r"^.*calendar.*$",url_parsed_path):
return False return False
elif parsed.query.find('ical') != -1: if parsed.query.find('ical') != -1:
return False return False
else: else:
return True return True