From f739ac4611c086473720a9882f5a56499ef1d818 Mon Sep 17 00:00:00 2001 From: Rubbit Date: Mon, 16 Sep 2024 00:24:57 +0800 Subject: [PATCH] first commit --- http-get.py | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) create mode 100644 http-get.py diff --git a/http-get.py b/http-get.py new file mode 100644 index 0000000..c0d317f --- /dev/null +++ b/http-get.py @@ -0,0 +1,33 @@ +import requests +from bs4 import BeautifulSoup + +# Define the URL +url = 'https://dictionary.cambridge.org/dictionary/essential-american-english/wrist' + +# Define the proxy settings +#proxies = { +# 'http': 'http://127.0.0.1:10809', +# 'https': 'http://127.0.0.1:10809' +#} +headers = { + 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36' +} +response = requests.get(url, headers=headers) + + +# Check if the request was successful +if response.status_code == 200: + # Parse the content with BeautifulSoup + soup = BeautifulSoup(response.content, 'html.parser') + + # Find the meta description tag + meta_description = soup.find('meta', attrs={'name': 'description'}) + + if meta_description: + # Extract the content attribute + description_content = meta_description.get('content') + print(description_content) + else: + print("Meta description tag not found.") +else: + print(f"Failed to retrieve the page. Status code: {response.status_code}")