diff options
Diffstat (limited to 'python/sandcrawler/html.py')
| -rw-r--r-- | python/sandcrawler/html.py | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/python/sandcrawler/html.py b/python/sandcrawler/html.py index 6236a3b..acf1522 100644 --- a/python/sandcrawler/html.py +++ b/python/sandcrawler/html.py @@ -105,7 +105,7 @@ def extract_fulltext_url(html_url, html_body): # http://www.jasstudies.com/DergiTamDetay.aspx?ID=3401 # <embed src="/files/jass_makaleler/1359848334_33-Okt.%20Yasemin%20KARADEM%C4%B0R.pdf" type="application/pdf" /> embed = soup.find('embed', attrs={"type": "application/pdf"}) - if embed: + if embed and embed.get('src'): url = embed['src'].strip() if url.startswith('/'): url = host_prefix+url |