Better lang detect, fetch parser handling, rss google news search
This commit is contained in:
186
1-DB.ipynb
186
1-DB.ipynb
@@ -2,7 +2,7 @@
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"execution_count": 23,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@@ -11,7 +11,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"execution_count": 24,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
@@ -20,108 +20,20 @@
|
||||
"text": [
|
||||
"db_postgres\n",
|
||||
"db_redis\n",
|
||||
"\u001b[1A\u001b[1B\u001b[0G\u001b[?25l[+] Running 0/0\n",
|
||||
" ⠙ matitos_dozzle Pulling \u001b[39m\u001b[0m \u001b[34m0.1s \u001b[0m\n",
|
||||
"\u001b[?25h\u001b[1A\u001b[1A\u001b[0G\u001b[?25l[+] Running 0/1\n",
|
||||
" ⠹ matitos_dozzle Pulling \u001b[39m\u001b[0m \u001b[34m0.2s \u001b[0m\n",
|
||||
"\u001b[?25h\u001b[1A\u001b[1A\u001b[0G\u001b[?25l[+] Running 0/1\n",
|
||||
" ⠸ matitos_dozzle Pulling \u001b[39m\u001b[0m \u001b[34m0.3s \u001b[0m\n",
|
||||
"\u001b[?25h\u001b[1A\u001b[1A\u001b[0G\u001b[?25l[+] Running 0/1\n",
|
||||
" ⠼ matitos_dozzle Pulling \u001b[39m\u001b[0m \u001b[34m0.4s \u001b[0m\n",
|
||||
"\u001b[?25h\u001b[1A\u001b[1A\u001b[0G\u001b[?25l[+] Running 0/1\n",
|
||||
" ⠴ matitos_dozzle Pulling \u001b[39m\u001b[0m \u001b[34m0.5s \u001b[0m\n",
|
||||
"\u001b[?25h\u001b[1A\u001b[1A\u001b[0G\u001b[?25l[+] Running 0/1\n",
|
||||
" ⠦ matitos_dozzle Pulling \u001b[39m\u001b[0m \u001b[34m0.6s \u001b[0m\n",
|
||||
"\u001b[?25h\u001b[1A\u001b[1A\u001b[0G\u001b[?25l[+] Running 0/1\n",
|
||||
" ⠧ matitos_dozzle Pulling \u001b[39m\u001b[0m \u001b[34m0.7s \u001b[0m\n",
|
||||
"\u001b[?25h\u001b[1A\u001b[1A\u001b[0G\u001b[?25l[+] Running 0/1\n",
|
||||
" ⠇ matitos_dozzle Pulling \u001b[39m\u001b[0m \u001b[34m0.8s \u001b[0m\n",
|
||||
"\u001b[?25h\u001b[1A\u001b[1A\u001b[0G\u001b[?25l[+] Running 0/1\n",
|
||||
" ⠏ matitos_dozzle Pulling \u001b[39m\u001b[0m \u001b[34m0.9s \u001b[0m\n",
|
||||
"\u001b[?25h\u001b[1A\u001b[1A\u001b[0G\u001b[?25l[+] Running 0/1\n",
|
||||
" ⠋ matitos_dozzle Pulling \u001b[39m\u001b[0m \u001b[34m1.0s \u001b[0m\n",
|
||||
"\u001b[?25h\u001b[1A\u001b[1A\u001b[0G\u001b[?25l[+] Running 0/1\n",
|
||||
" ⠙ matitos_dozzle Pulling \u001b[39m\u001b[0m \u001b[34m1.1s \u001b[0m\n",
|
||||
"\u001b[?25h\u001b[1A\u001b[1A\u001b[0G\u001b[?25l[+] Running 0/1\n",
|
||||
" ⠹ matitos_dozzle Pulling \u001b[39m\u001b[0m \u001b[34m1.2s \u001b[0m\n",
|
||||
"\u001b[?25h\u001b[1A\u001b[1A\u001b[0G\u001b[?25l[+] Running 0/1\n",
|
||||
" ⠸ matitos_dozzle Pulling \u001b[39m\u001b[0m \u001b[34m1.3s \u001b[0m\n",
|
||||
"\u001b[?25h\u001b[1A\u001b[1A\u001b[0G\u001b[?25l[+] Running 0/1\n",
|
||||
" ⠼ matitos_dozzle Pulling \u001b[39m\u001b[0m \u001b[34m1.4s \u001b[0m\n",
|
||||
"\u001b[?25h\u001b[1A\u001b[1A\u001b[0G\u001b[?25l[+] Running 0/1\n",
|
||||
" ⠴ matitos_dozzle Pulling \u001b[39m\u001b[0m \u001b[34m1.5s \u001b[0m\n",
|
||||
"\u001b[?25h\u001b[1A\u001b[1A\u001b[0G\u001b[?25l[+] Running 0/1\n",
|
||||
" ⠦ matitos_dozzle Pulling \u001b[39m\u001b[0m \u001b[34m1.6s \u001b[0m\n",
|
||||
"\u001b[?25h\u001b[1A\u001b[1A\u001b[0G\u001b[?25l[+] Running 0/1\n",
|
||||
" ⠧ matitos_dozzle Pulling \u001b[39m\u001b[0m \u001b[34m1.7s \u001b[0m\n",
|
||||
"\u001b[?25h\u001b[1A\u001b[1A\u001b[0G\u001b[?25l[+] Running 0/1\n",
|
||||
" ⠇ matitos_dozzle \u001b[33m3 layers\u001b[0m [\u001b[32m\u001b[1m⠀⠀⠀\u001b[0m] 0B/0B Pulling \u001b[39m\u001b[0m \u001b[34m1.8s \u001b[0m\n",
|
||||
" ⠋ b5b68a794063 Pulling fs layer \u001b[39m\u001b[0m \u001b[34m0.0s \u001b[0m\n",
|
||||
" ⠋ 764914624645 Pulling fs layer \u001b[39m\u001b[0m \u001b[34m0.0s \u001b[0m\n",
|
||||
" ⠋ 82780b9b6d69 Pulling fs layer \u001b[39m\u001b[0m \u001b[34m0.0s \u001b[0m\n",
|
||||
"\u001b[?25h\u001b[1A\u001b[1A\u001b[1A\u001b[1A\u001b[1A\u001b[0G\u001b[?25l[+] Running 0/4\n",
|
||||
" ⠏ matitos_dozzle \u001b[33m3 layers\u001b[0m [\u001b[32m\u001b[1m⠀⠀⠀\u001b[0m] 0B/0B Pulling \u001b[39m\u001b[0m \u001b[34m1.9s \u001b[0m\n",
|
||||
" ⠙ b5b68a794063 Pulling fs layer \u001b[39m\u001b[0m \u001b[34m0.1s \u001b[0m\n",
|
||||
" ⠙ 764914624645 Pulling fs layer \u001b[39m\u001b[0m \u001b[34m0.1s \u001b[0m\n",
|
||||
" ⠙ 82780b9b6d69 Pulling fs layer \u001b[39m\u001b[0m \u001b[34m0.1s \u001b[0m\n",
|
||||
"\u001b[?25h\u001b[1A\u001b[1A\u001b[1A\u001b[1A\u001b[1A\u001b[0G\u001b[?25l[+] Running 0/4\n",
|
||||
" ⠋ matitos_dozzle \u001b[33m3 layers\u001b[0m [\u001b[32m\u001b[1m⠀⠀⠀\u001b[0m] 0B/0B Pulling \u001b[39m\u001b[0m \u001b[34m2.0s \u001b[0m\n",
|
||||
" ⠹ b5b68a794063 Pulling fs layer \u001b[39m\u001b[0m \u001b[34m0.2s \u001b[0m\n",
|
||||
" ⠹ 764914624645 Pulling fs layer \u001b[39m\u001b[0m \u001b[34m0.2s \u001b[0m\n",
|
||||
" ⠹ 82780b9b6d69 Pulling fs layer \u001b[39m\u001b[0m \u001b[34m0.2s \u001b[0m\n",
|
||||
"\u001b[?25h\u001b[1A\u001b[1A\u001b[1A\u001b[1A\u001b[1A\u001b[0G\u001b[?25l[+] Running 0/4\n",
|
||||
" ⠙ matitos_dozzle \u001b[33m3 layers\u001b[0m [\u001b[32m\u001b[1m⠀⠀⠀\u001b[0m] 0B/0B Pulling \u001b[39m\u001b[0m \u001b[34m2.1s \u001b[0m\n",
|
||||
" ⠸ b5b68a794063 Pulling fs layer \u001b[39m\u001b[0m \u001b[34m0.3s \u001b[0m\n",
|
||||
" ⠸ 764914624645 Pulling fs layer \u001b[39m\u001b[0m \u001b[34m0.3s \u001b[0m\n",
|
||||
" ⠸ 82780b9b6d69 Pulling fs layer \u001b[39m\u001b[0m \u001b[34m0.3s \u001b[0m\n",
|
||||
"\u001b[?25h\u001b[1A\u001b[1A\u001b[1A\u001b[1A\u001b[1A\u001b[0G\u001b[?25l[+] Running 1/4\n",
|
||||
" ⠹ matitos_dozzle \u001b[33m3 layers\u001b[0m [\u001b[32m\u001b[1m⣿⠀⠀\u001b[0m] 0B/0B Pulling \u001b[39m\u001b[0m \u001b[34m2.2s \u001b[0m\n",
|
||||
" \u001b[32m✔\u001b[0m b5b68a794063 Pull complete \u001b[32m\u001b[0m \u001b[34m0.4s \u001b[0m\n",
|
||||
" ⠼ 764914624645 Pulling fs layer \u001b[39m\u001b[0m \u001b[34m0.4s \u001b[0m\n",
|
||||
" ⠼ 82780b9b6d69 Pulling fs layer \u001b[39m\u001b[0m \u001b[34m0.4s \u001b[0m\n",
|
||||
"\u001b[?25h\u001b[1A\u001b[1A\u001b[1A\u001b[1A\u001b[1A\u001b[0G\u001b[?25l[+] Running 2/4\n",
|
||||
" ⠸ matitos_dozzle \u001b[33m3 layers\u001b[0m [\u001b[32m\u001b[1m⣿⣿⠀\u001b[0m] 166.8kB/16.38MB Pulling \u001b[39m\u001b[0m \u001b[34m2.3s \u001b[0m\n",
|
||||
" \u001b[32m✔\u001b[0m b5b68a794063 Pull complete \u001b[32m\u001b[0m \u001b[34m0.4s \u001b[0m\n",
|
||||
" \u001b[32m✔\u001b[0m 764914624645 Pull complete \u001b[32m\u001b[0m \u001b[34m0.4s \u001b[0m\n",
|
||||
" ⠴ 82780b9b6d69 Downloading \u001b[39m 166.8kB/16.38MB\u001b[0m \u001b[34m0.5s \u001b[0m\n",
|
||||
"\u001b[?25h\u001b[1A\u001b[1A\u001b[1A\u001b[1A\u001b[1A\u001b[0G\u001b[?25l[+] Running 2/4\n",
|
||||
" ⠼ matitos_dozzle \u001b[33m3 layers\u001b[0m [\u001b[32m\u001b[1m⣿⣿⣤\u001b[0m] 9.833MB/16.38MB Pulling \u001b[39m\u001b[0m \u001b[34m2.4s \u001b[0m\n",
|
||||
" \u001b[32m✔\u001b[0m b5b68a794063 Pull complete \u001b[32m\u001b[0m \u001b[34m0.4s \u001b[0m\n",
|
||||
" \u001b[32m✔\u001b[0m 764914624645 Pull complete \u001b[32m\u001b[0m \u001b[34m0.4s \u001b[0m\n",
|
||||
" ⠦ 82780b9b6d69 Downloading \u001b[39m 9.833MB/16.38MB\u001b[0m \u001b[34m0.6s \u001b[0m\n",
|
||||
"\u001b[?25h\u001b[1A\u001b[1A\u001b[1A\u001b[1A\u001b[1A\u001b[0G\u001b[?25l[+] Running 2/4\n",
|
||||
" ⠴ matitos_dozzle \u001b[33m3 layers\u001b[0m [\u001b[32m\u001b[1m⣿⣿⠀\u001b[0m] 163.8kB/16.38MB Pulling \u001b[39m\u001b[0m \u001b[34m2.5s \u001b[0m\n",
|
||||
" \u001b[32m✔\u001b[0m b5b68a794063 Pull complete \u001b[32m\u001b[0m \u001b[34m0.4s \u001b[0m\n",
|
||||
" \u001b[32m✔\u001b[0m 764914624645 Pull complete \u001b[32m\u001b[0m \u001b[34m0.4s \u001b[0m\n",
|
||||
" ⠿ 82780b9b6d69 Extracting \u001b[39m 163.8kB/16.38MB\u001b[0m \u001b[34m0.7s \u001b[0m\n",
|
||||
"\u001b[?25h\u001b[1A\u001b[1A\u001b[1A\u001b[1A\u001b[1A\u001b[0G\u001b[?25l[+] Running 2/4\n",
|
||||
" ⠦ matitos_dozzle \u001b[33m3 layers\u001b[0m [\u001b[32m\u001b[1m⣿⣿⣤\u001b[0m] 9.667MB/16.38MB Pulling \u001b[39m\u001b[0m \u001b[34m2.6s \u001b[0m\n",
|
||||
" \u001b[32m✔\u001b[0m b5b68a794063 Pull complete \u001b[32m\u001b[0m \u001b[34m0.4s \u001b[0m\n",
|
||||
" \u001b[32m✔\u001b[0m 764914624645 Pull complete \u001b[32m\u001b[0m \u001b[34m0.4s \u001b[0m\n",
|
||||
" ⠿ 82780b9b6d69 Extracting \u001b[39m 9.667MB/16.38MB\u001b[0m \u001b[34m0.8s \u001b[0m\n",
|
||||
"\u001b[?25h\u001b[1A\u001b[1A\u001b[1A\u001b[1A\u001b[1A\u001b[0G\u001b[?25l\u001b[34m[+] Running 4/4\u001b[0m\n",
|
||||
" \u001b[32m✔\u001b[0m matitos_dozzle \u001b[33m3 layers\u001b[0m [\u001b[32m\u001b[1m⣿⣿⣿\u001b[0m] 0B/0B Pulled \u001b[32m\u001b[0m \u001b[34m2.7s \u001b[0m\n",
|
||||
" \u001b[32m✔\u001b[0m b5b68a794063 Pull complete \u001b[32m\u001b[0m \u001b[34m0.4s \u001b[0m\n",
|
||||
" \u001b[32m✔\u001b[0m 764914624645 Pull complete \u001b[32m\u001b[0m \u001b[34m0.4s \u001b[0m\n",
|
||||
" \u001b[32m✔\u001b[0m 82780b9b6d69 Pull complete \u001b[32m\u001b[0m \u001b[34m0.9s \u001b[0m\n",
|
||||
"\u001b[?25h\u001b[1A\u001b[1B\u001b[0G\u001b[?25l[+] Running 0/0\n",
|
||||
" ⠋ Container db_redis \u001b[39mCreating\u001b[0m \u001b[34m0.0s \u001b[0m\n",
|
||||
" ⠋ Container db_postgres \u001b[39mCreating\u001b[0m \u001b[34m0.0s \u001b[0m\n",
|
||||
" ⠋ Container dozzle \u001b[39mCreating\u001b[0m \u001b[34m0.0s \u001b[0m\n",
|
||||
"\u001b[?25h\u001b[1A\u001b[1A\u001b[1A\u001b[1A\u001b[0G\u001b[?25l[+] Running 1/3\n",
|
||||
"\u001b[1A\u001b[1B\u001b[0G\u001b[?25l[+] Running 2/0\n",
|
||||
" ⠿ Container db_redis \u001b[39mStarting\u001b[0m \u001b[34m0.1s \u001b[0m\n",
|
||||
" ⠿ Container db_postgres \u001b[39mStarting\u001b[0m \u001b[34m0.1s \u001b[0m\n",
|
||||
" ⠿ Container dozzle \u001b[39mStarting\u001b[0m \u001b[34m0.1s \u001b[0m\n",
|
||||
" \u001b[32m✔\u001b[0m Container dozzle \u001b[32mRunning\u001b[0m \u001b[34m0.0s \u001b[0m\n",
|
||||
" \u001b[32m✔\u001b[0m Container adminer \u001b[32mRunning\u001b[0m \u001b[34m0.0s \u001b[0m\n",
|
||||
"\u001b[?25h\u001b[1A\u001b[1A\u001b[1A\u001b[1A\u001b[1A\u001b[0G\u001b[?25l[+] Running 1/4\n",
|
||||
"\u001b[?25h\u001b[1A\u001b[1A\u001b[1A\u001b[1A\u001b[1A\u001b[0G\u001b[?25l[+] Running 2/4\n",
|
||||
" ⠿ Container db_redis \u001b[39mStarting\u001b[0m \u001b[34m0.2s \u001b[0m\n",
|
||||
" ⠿ Container db_postgres \u001b[39mStarting\u001b[0m \u001b[34m0.2s \u001b[0m\n",
|
||||
" ⠿ Container dozzle \u001b[39mStarting\u001b[0m \u001b[34m0.2s \u001b[0m\n",
|
||||
" \u001b[32m✔\u001b[0m Container dozzle \u001b[32mRunning\u001b[0m \u001b[34m0.0s \u001b[0m\n",
|
||||
" \u001b[32m✔\u001b[0m Container adminer \u001b[32mRunning\u001b[0m \u001b[34m0.0s \u001b[0m\n",
|
||||
"\u001b[?25h\u001b[1A\u001b[1A\u001b[1A\u001b[1A\u001b[1A\u001b[0G\u001b[?25l\u001b[34m[+] Running 4/4\u001b[0m\n",
|
||||
" \u001b[32m✔\u001b[0m Container db_redis \u001b[32mStarted\u001b[0m \u001b[34m0.3s \u001b[0m\n",
|
||||
" \u001b[32m✔\u001b[0m Container db_postgres \u001b[32mStarted\u001b[0m \u001b[34m0.3s \u001b[0m\n",
|
||||
" \u001b[32m✔\u001b[0m Container dozzle \u001b[32mStarted\u001b[0m \u001b[34m0.3s \u001b[0m\n",
|
||||
" \u001b[32m✔\u001b[0m Container db_redis \u001b[32mStarted\u001b[0m \u001b[34m0.2s \u001b[0m\n",
|
||||
" \u001b[32m✔\u001b[0m Container db_postgres \u001b[32mStarted\u001b[0m \u001b[34m0.2s \u001b[0m\n",
|
||||
" \u001b[32m✔\u001b[0m Container dozzle \u001b[32mRunning\u001b[0m \u001b[34m0.0s \u001b[0m\n",
|
||||
" \u001b[32m✔\u001b[0m Container adminer \u001b[32mRunning\u001b[0m \u001b[34m0.0s \u001b[0m\n",
|
||||
"\u001b[?25h"
|
||||
]
|
||||
@@ -133,7 +45,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"execution_count": 25,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@@ -145,8 +57,15 @@
|
||||
"\n",
|
||||
"from datetime import datetime, timezone\n",
|
||||
"import re\n",
|
||||
"from pprint import pprint\n",
|
||||
"\n",
|
||||
"from pprint import pprint"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 26,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"if INSERT_TABLES:\n",
|
||||
" # Connect to an existing database\n",
|
||||
" with psycopg.connect(connection_info) as conn:\n",
|
||||
@@ -234,9 +153,9 @@
|
||||
" # Feeds\n",
|
||||
" cur.execute( \"INSERT INTO SEARCH (search, type) VALUES ('https://api.missingkids.org/missingkids/servlet/XmlServlet?act=rss&LanguageCountry=en_US&orgPrefix=NCMC', 'rss_feed');\" )\n",
|
||||
" # Websites of interest\n",
|
||||
" cur.execute( \"INSERT INTO SEARCH (search, type) VALUES ('www.missingkids.org/poster', 'url_host');\" )\n",
|
||||
" cur.execute( \"INSERT INTO SEARCH (search, type) VALUES ('www.breitbart.com', 'url_host');\" )\n",
|
||||
" cur.execute( \"INSERT INTO SEARCH (search, type) VALUES ('missingkids.org/poster', 'url_host');\" )\n",
|
||||
" cur.execute( \"INSERT INTO SEARCH (search, type) VALUES ('missingkids.org/new-poster', 'url_host');\" )\n",
|
||||
" cur.execute( \"INSERT INTO SEARCH (search, type) VALUES ('breitbart.com', 'url_host');\" )\n",
|
||||
" # Search keywords\n",
|
||||
" cur.execute( \"INSERT INTO SEARCH (search, type) VALUES ('child abuse', 'keyword_search');\" )\n",
|
||||
" \n",
|
||||
@@ -252,7 +171,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"execution_count": 27,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@@ -304,7 +223,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"execution_count": 28,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
@@ -323,8 +242,10 @@
|
||||
"[(1,\n",
|
||||
" 'https://api.missingkids.org/missingkids/servlet/XmlServlet?act=rss&LanguageCountry=en_US&orgPrefix=NCMC',\n",
|
||||
" 'rss_feed'),\n",
|
||||
" (2, 'www.breitbart.com', 'url_host'),\n",
|
||||
" (3, 'child abuse', 'keyword_search')]\n",
|
||||
" (2, 'missingkids.org/poster', 'url_host'),\n",
|
||||
" (3, 'missingkids.org/new-poster', 'url_host'),\n",
|
||||
" (4, 'breitbart.com', 'url_host'),\n",
|
||||
" (5, 'child abuse', 'keyword_search')]\n",
|
||||
"\t status_pattern_matching\n",
|
||||
"[('.*youtube\\\\.com/.*', 50, 'invalid'),\n",
|
||||
" ('.*tiktok\\\\.com/.*', 50, 'invalid'),\n",
|
||||
@@ -353,7 +274,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"execution_count": 29,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
@@ -363,8 +284,10 @@
|
||||
"[(1,\n",
|
||||
" 'https://api.missingkids.org/missingkids/servlet/XmlServlet?act=rss&LanguageCountry=en_US&orgPrefix=NCMC',\n",
|
||||
" 'rss_feed'),\n",
|
||||
" (2, 'www.breitbart.com', 'url_host'),\n",
|
||||
" (3, 'child abuse', 'keyword_search')]\n"
|
||||
" (2, 'missingkids.org/poster', 'url_host'),\n",
|
||||
" (3, 'missingkids.org/new-poster', 'url_host'),\n",
|
||||
" (4, 'breitbart.com', 'url_host'),\n",
|
||||
" (5, 'child abuse', 'keyword_search')]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
@@ -378,7 +301,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"execution_count": 30,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
@@ -397,6 +320,49 @@
|
||||
" pprint( cur.execute(\"SELECT * FROM URLS LIMIT 150;\").fetchall() )\n",
|
||||
" #pprint( cur.execute(\"SELECT id_url, title, valid_content FROM URL_CONTENT LIMIT 10;\").fetchall() )"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 31,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'\\n!docker rm -f db_redis; docker compose -f docker/docker-compose.yml up -d\\n\\n# Connect to an existing database\\nwith psycopg.connect(connection_info) as conn:\\n # Open a cursor to perform database operations\\n with conn.cursor() as cur:\\n pprint( cur.execute(\"TRUNCATE URLS, URL_CONTENT, URLS_SOURCE_SEARCH, URLS_DUPLICATE;\") )\\n # cur.execute( \"INSERT INTO SEARCH (search, type) VALUES (\\'missingkids.org\\', \\'url_host\\');\" )\\n'"
|
||||
]
|
||||
},
|
||||
"execution_count": 31,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"'''\n",
|
||||
"!docker rm -f db_redis; docker compose -f docker/docker-compose.yml up -d\n",
|
||||
"\n",
|
||||
"# Connect to an existing database\n",
|
||||
"with psycopg.connect(connection_info) as conn:\n",
|
||||
" # Open a cursor to perform database operations\n",
|
||||
" with conn.cursor() as cur:\n",
|
||||
" pprint( cur.execute(\"TRUNCATE URLS, URL_CONTENT, URLS_SOURCE_SEARCH, URLS_DUPLICATE;\") )\n",
|
||||
" # cur.execute( \"INSERT INTO SEARCH (search, type) VALUES ('missingkids.org', 'url_host');\" )\n",
|
||||
"'''"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
|
||||
Reference in New Issue
Block a user