Move absolutify_links function to external file

1 files changed, 18 insertions, 0 deletions

diff --git a/utils/utils.py b/utils/utils.py
index bf3d4fbe..a82c23e6 100644
--- a/utils/utils.py
+++ b/utils/utils.py
@@ -7,6 +7,9 @@ import time
 import datetime
 import dateutil.tz
 
+import bs4
+import urllib.parse
+
 
 @contextmanager
 def init_colorama():
@@ -34,3 +37,18 @@ def current_datetime():
     """
     return datetime.datetime.fromtimestamp(round(time.time()),
                                            dateutil.tz.tzlocal())
+
+
+def absolutify_links(soup, baseurl):
+    """Make links in an article absolute.
+
+    Parameters
+    ----------
+    soup : bs4.BeautifulSoup
+    baseurl : str
+
+    """
+    for tag in soup.find_all(lambda tag: tag.has_attr("href")):
+        tag["href"] = urllib.parse.urljoin(baseurl, tag["href"])
+    for tag in soup.find_all(lambda tag: tag.has_attr("src")):
+        tag["src"] = urllib.parse.urljoin(baseurl, tag["src"])