From f5a3b03874c472494230cfd97b69af47dc57dac9 Mon Sep 17 00:00:00 2001
From: Daniel Hladek <daniel.hladek@tuke.sk>
Date: Sun, 30 Apr 2023 13:54:36 +0200
Subject: [PATCH] zz

---
 mongo/cli.py          | 11 ++++++++++-
 mongo/mongocrawler.py |  9 ++++++++-
 2 files changed, 18 insertions(+), 2 deletions(-)

diff --git a/mongo/cli.py b/mongo/cli.py
index 66cc1e7..8dc2d7f 100644
--- a/mongo/cli.py
+++ b/mongo/cli.py
@@ -9,26 +9,35 @@ REDIS_URL= os.getenv("REDIS_URL","redis://localhost:6379/")
 QUEUES=os.getenv("QUEUES","high,default,low")
 
 @click.group()
-def cli():
+@click.option("--dbname",default=mongocrawler.DBNAME,help="database to use")
+def cli(dbname):
+    DBNAME=dbname
     pass
 
 @cli.command()
 def createdb():
     mongocrawler.createdb()
 
+@cli.command()
+def dropdb():
+    mongocrawler.dropdb()
+
 @cli.command()
 @click.argument("link")
 def parseurl(link):
+    """ Parse document on link for debug """
     mongocrawler.parseurl(link)
 
 @cli.command()
 @click.argument("link")
 def externaldomains(link):
+    """ Extract external domains from link """
     mongocrawler.externaldomains(link)
 
 @cli.command()
 @click.argument("start_link")
 def classify(start_link):
+    """ domain to  to classify links for debug """
     mongocrawler.classify(start_link)
 
 @cli.command()
diff --git a/mongo/mongocrawler.py b/mongo/mongocrawler.py
index 3ab4478..24e9ef1 100644
--- a/mongo/mongocrawler.py
+++ b/mongo/mongocrawler.py
@@ -87,6 +87,7 @@ def get_bs_links(link,html):
             print(err)
             pass
     return links
+
 def split_train(res):
     trainset = []
     testset = []
@@ -209,7 +210,7 @@ def fetch_robot(base_url:str)->urllib.robotparser.RobotFileParser:
 def extract_page(final_link,html):
     doc = None
     if html is not None:
-        doc = trafilatura.bare_extraction(html,url=final_link,with_metadata=True,include_formatting=True,target_language=LANGUAGE,favor_precision=True)
+        doc = trafilatura.bare_extraction(html,url=final_link,with_metadata=True,include_formatting=False,target_language=LANGUAGE,favor_precision=True)
         if doc is not None:
             if not "text" in doc or len(doc["text"]) < MIN_TEXT_SIZE:
                 # text too small
@@ -602,6 +603,12 @@ def domain_summary(db,hostname):
     for item in res:
         print(item)
 
+def dropdb():
+    myclient = pymongo.MongoClient(CONNECTION)
+    print("write name of database to drop")
+    dbname = sys.stdin.readline().strip()
+    myclient.drop_database(dbname)
+
 
 def createdb():
     myclient = pymongo.MongoClient(CONNECTION)