Skip to content

A Smart, Automatic, Fast and Lightweight Web Scraper for Python

Remove unused get_random_str

Mikaeec33398f292
diff --git a/autoscraper/auto_scraper.py b/autoscraper/auto_scraper.py
index 4227e6b..73f90a6 100644
--- a/autoscraper/auto_scraper.py
+++ b/autoscraper/auto_scraper.py
@@ -11,7 +11,6 @@ from autoscraper.utils import (
FuzzyText,
ResultItem,
get_non_rec_text,
- get_random_str,
normalize,
text_match,
unique_hashable,
@@ -294,7 +293,7 @@ class AutoScraper(object):
)
stack["url"] = url if is_full_url else ""
stack["hash"] = hashlib.sha256(str(stack).encode("utf-8")).hexdigest()
- stack["stack_id"] = "rule_" + get_random_str(4)
+ stack["stack_id"] = "rule_" + stack["hash"][:8]
return stack
def _get_result_for_child(self, child, soup, url):
diff --git a/autoscraper/utils.py b/autoscraper/utils.py
index 5193708..15641f6 100644
--- a/autoscraper/utils.py
+++ b/autoscraper/utils.py
@@ -1,7 +1,5 @@
from collections import OrderedDict
-import random
-import string
import unicodedata
from difflib import SequenceMatcher
@@ -24,11 +22,6 @@ def unique_hashable(hashable_items):
return list(OrderedDict.fromkeys(hashable_items))
-def get_random_str(n):
- chars = string.ascii_lowercase + string.digits
- return ''.join(random.choice(chars) for i in range(n))
-
-
def get_non_rec_text(element):
return ''.join(element.find_all(text=True, recursive=False)).strip()