Vivekananda_session1_4vp19cs095_sonam

homework

@@ -0,0 +1 @@
+

homework1/Dockerfile

@@ -0,0 +1,9 @@
+FROM python:3.10.2-alpine3.15
+# Create directories  
+RUN mkdir -p /root/workspace/src
+COPY ./web_scrapping.py  /root/workspace/src
+# Switch to project directory
+WORKDIR /root/workspace/src
+# Install required packages
+RUN pip install --upgrade pip
+RUN pip install requests bs4 html5lib

homework1/connect.py

@@ -0,0 +1,25 @@
+import psycopg2
+import csv
+conn = psycopg2.connect(
+    host="172.17.0.2",
+    port="5432",
+    dbname="web_scrape",
+    user="postgres",
+    password="123456"
+)
+
+cur = conn.cursor()
+
+with open('output.csv','r') as f:
+ csv_reader = csv.reader(f)
+ next(csv_reader)
+ for row in csv_reader:
+     if row[1] =="":
+       row[1] = "N/A"
+
+     cur.execute("INSERT INTO demo  (column1, column2, column3) VALUES (%s, %s, %s)",(row[0], row[1],row[2]))
+
+conn.commit()
+
+cur.close()
+conn.close()

homework1/docker-compose.yml

@@ -0,0 +1,9 @@
+psql-db:
+  image: 'postgres:14'
+  container_name: psql-db
+  environment:
+    - PGPASSWORD=123456
+    - POSTGRES_USER=postgres
+    - POSTGRES_PASSWORD=123456
+  ports:
+    - '5434:5432'

homework1/output.csv

@@ -0,0 +1,12 @@
+column 1,column 2,column 3
+"Major new features of the 3.12 series, compared to 3.11",And now for something completely different,"<span style=""font-size: medium;"">Major new features of the 3.12 series, compared to 3.11</span>"
+More resources,"<span style=""font-size: medium;"">More resources</span>",Enjoy the new releases
+<br/>,And now for something completely different,<br/>
+,"Major new features of the 3.12 series, compared to 3.11",
+Enjoy the new releases,More resources,
+"Major new features of the 3.12 series, compared to 3.11",,
+More resources,,
+<br/>,,
+And now for something completely different,,
+<br/>,,
+Enjoy the new releases,,

homework1/web_scrapping.py

@@ -0,0 +1,12 @@
+import requests
+import csv
+from bs4 import BeautifulSoup
+res=requests.get("https://blog.python.org/")
+soup = BeautifulSoup(res.content, "html.parser")
+titles = soup.find_all("h1")
+with open('output.csv','w',newline='') as f:
+ writer = csv.writer(f)
+ writer.writerow(['column 1','column 2','column 3'])
+ for row in titles:
+   writer.writerow(row)
+f.close()