Upload 3 files
Browse files- Dockerfile +20 -0
- main.py +21 -0
- requirements.txt +4 -0
Dockerfile
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
FROM python:3.10
|
| 2 |
+
|
| 3 |
+
RUN useradd -m -u 1000 user
|
| 4 |
+
USER user
|
| 5 |
+
ENV PATH="/home/user/.local/bin:${PATH}"
|
| 6 |
+
WORKDIR /app
|
| 7 |
+
COPY --chown=user . /app
|
| 8 |
+
USER root
|
| 9 |
+
|
| 10 |
+
RUN apt-get update && apt-get install -y wget unzip && \
|
| 11 |
+
wget https://dl.google.com/linux/direct/google-chrome-stable_current_amd64.deb && \
|
| 12 |
+
apt install -y ./google-chrome-stable_current_amd64.deb && \
|
| 13 |
+
rm google-chrome-stable_current_amd64.deb && \
|
| 14 |
+
apt-get clean
|
| 15 |
+
|
| 16 |
+
USER user
|
| 17 |
+
RUN pip install --trusted-host pypi.python.org -r requirements.txt
|
| 18 |
+
COPY --chown=user . .
|
| 19 |
+
|
| 20 |
+
CMD ["python", "main.py" ]
|
main.py
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import time
|
| 2 |
+
from bs4 import BeautifulSoup
|
| 3 |
+
from selenium import webdriver
|
| 4 |
+
from selenium.webdriver.chrome.service import Service
|
| 5 |
+
from selenium.webdriver.chrome.options import Options
|
| 6 |
+
from webdriver_manager.chrome import ChromeDriverManager
|
| 7 |
+
chrome_options = Options()
|
| 8 |
+
chrome_options.add_argument('--no-sandbox')
|
| 9 |
+
chrome_options.add_argument('--headless')
|
| 10 |
+
chrome_options.add_argument('--disable-gpu')
|
| 11 |
+
chrome_options.add_argument('--disable-dev-shm-usage')
|
| 12 |
+
driver = webdriver.Chrome(service=Service(ChromeDriverManager().install()),options=chrome_options)
|
| 13 |
+
url= 'https://navpan2-dockerbot.hf.space/'
|
| 14 |
+
driver.get(url)
|
| 15 |
+
time.sleep(5)
|
| 16 |
+
soup = BeautifulSoup(driver.page_source,'lxml')
|
| 17 |
+
headings = soup.find_all( name= 'span')
|
| 18 |
+
for heading in headings:
|
| 19 |
+
print(heading.getText())
|
| 20 |
+
time.sleep(2)
|
| 21 |
+
driver.quit()
|
requirements.txt
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
selenium
|
| 2 |
+
beautifulsoup4
|
| 3 |
+
webdriver_manager
|
| 4 |
+
lxml
|