Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 5 additions & 13 deletions Dockerfile
Original file line number Diff line number Diff line change
@@ -1,17 +1,9 @@
FROM python:3.10.2-alpine3.15
COPY . .
# Install Postgres
RUN apk update
RUN apk add postgresql
RUN chown postgres:postgres /run/postgresql/
# Install requirements
COPY ./requirements.txt /tmp
RUN pip install -r /tmp/requirements.txt
# For psycopg2
RUN apk add --virtual postgresql-deps libpq-dev
# Create directories
RUN mkdir -p /root/workspace/src
# Mount your local file
COPY ./web_scraping_sample.py /root/workspace/src
COPY ./webScraping.py /root/workspace/src
# Switch to project directory
WORKDIR /root/workspace/src
WORKDIR /root/workspace/src
# Install required packages
RUN pip install --upgrade pip
RUN pip install requests bs4 html5lib psycopg2-binary
9 changes: 9 additions & 0 deletions HOMEWORK/Dockerfile
Original file line number Diff line number Diff line change
@@ -0,0 +1,9 @@
FROM python:3.10.2-alpine3.15
# Create directories
RUN mkdir -p /root/workspace/src
COPY ./webScraping.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 psycopg2-binary
10 changes: 10 additions & 0 deletions HOMEWORK/docker-compose.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,10 @@

psql-db:
image: 'postgres:14'
container_name: psql-db
environment:
- PGPASSWORD=123456
- POSTGRES_USER=postgres
- POSTGRES_PASSWORD=123456
ports:
- '5434:5432'
33 changes: 33 additions & 0 deletions HOMEWORK/webScraping.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,33 @@
import requests
from bs4 import BeautifulSoup
import re
import psycopg2
conn = psycopg2.connect(
host="172.17.0.2",
port="5432",
database="pybd",
user="postgres",
password="123456"
)
print("Connection Successful")
cur = conn.cursor()
res = requests.get('https://blog.python.org/')
soup = BeautifulSoup(res.content, 'html5lib')
titles=[]
authors=[]
for i in soup.find_all('h3', class_='entry-title'):

string = i.find('a').getText()
titles.append(string.strip())
for i in soup.find_all('span', class_='fn'):
string = i.getText()
authors.append(string.strip())
for i in range(4):
cur.execute(
"CREATE TABLE py1(no INT, title VARCHAR(100),author VARCHAR(100));"
"INSERT INTO py1(no,title,author) VALUES(%s,%s,%s)", (i+1, titles[i], authors[i])
)
conn.commit()
cur.close()
conn.close()

10 changes: 10 additions & 0 deletions docker-compose.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,10 @@

psql-db:
image: 'postgres:14'
container_name: psql-db
environment:
- PGPASSWORD=123456
- POSTGRES_USER=postgres
- POSTGRES_PASSWORD=123456
ports:
- '5434:5432'
32 changes: 32 additions & 0 deletions webScraping.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,32 @@
import requests
from bs4 import BeautifulSoup
import re
import psycopg2
conn = psycopg2.connect(
host="172.17.0.2",
port="5432",
database="pybd",
user="postgres",
password="123456"
)
print("Connection Successful")
cur = conn.cursor()
res = requests.get('https://blog.python.org/')
soup = BeautifulSoup(res.content, 'html5lib')
titles=[]
authors=[]
for i in soup.find_all('h3', class_='entry-title'):

string = i.find('a').getText()
titles.append(string.strip())
for i in soup.find_all('span', class_='fn'):
string = i.getText()
authors.append(string.strip())
for i in range(4):
cur.execute(
"INSERT INTO py1(no,title,author) VALUES(%s,%s,%s)", (i+1, titles[i], authors[i])
)
conn.commit()
cur.close()
conn.close()