Allow images to be embedded from document

1 files changed, 12 insertions, 2 deletions

diff --git a/src/scrape_lexicanum.py b/src/scrape_lexicanum.py
index a719fb1..88001a3 100644
--- a/src/scrape_lexicanum.py
+++ b/src/scrape_lexicanum.py
@@ -7,6 +7,9 @@ import requests
 class WikiError(Exception):
     pass
 
+def fix_link(config, node, field):
+    node[field] = node[field].replace("/wiki", config["site"] + "/wiki")
+
 def get_search_response(config, query):
     try:
         response = requests.get(config['site'] + '/mediawiki/api.php?action=opensearch&format=json&formatversion=2&search=' + query + '&namespace=0&limit=6&suggest=true', timeout=7)
@@ -49,10 +52,17 @@ def get_page_content(config, page_name):
     parser_output = soup.find(id="mw-content-text").contents[0]
     content = parser_output.find("p")
     for a in content.findAll("a"):
-        a["href"] = a["href"].replace("/wiki", config["site"] + "/wiki")
+        fix_link(config, a, "href")
+
+    image = parser_output.find("a", {"class": "image"})
+    image_link = None
+    if image:
+        if image.contents[0]:
+            fix_link(config, image.contents[0], "src")
+            image_link = image.contents[0]["src"]
 
     header_md = markdownify(str(soup.find(id="firstHeading").contents[0]))
     content_md = markdownify(str(content))
 
-    return header_md, content_md
+    return header_md, content_md, image_link