35 lines
994 B
Markdown
35 lines
994 B
Markdown
```python
|
|
# %%
|
|
import os; os.system('pip install -q requests bs4 lxml pandas')
|
|
import requests, bs4, json, pandas as pd
|
|
|
|
def ollama(prompt):
|
|
return requests.post(
|
|
"https://ollama.yauk.tv/api/generate",
|
|
json={
|
|
"model": "llama3.1",
|
|
"format": "json",
|
|
"prompt": prompt,
|
|
"stream": False,
|
|
"options": {
|
|
"temperature": 0,
|
|
"num_ctx": 32768
|
|
}
|
|
}
|
|
).json()['response']
|
|
|
|
# %%
|
|
url = 'https://ollama.com/library'
|
|
response = requests.get(url)
|
|
soup = bs4.BeautifulSoup(response.text, 'lxml')
|
|
tags = ''.join(str(tag.prettify()) for tag in soup.find_all('li', class_='flex')[:20])
|
|
print(tags)
|
|
|
|
# %%
|
|
result = ollama(f''' Parse the following HTML snippet and extract the information into a JSON format. Output only the JSON data, without any additional text, explanation, or formatting.
|
|
|
|
HTML to analyze: {tags} ''')
|
|
|
|
df = pd.DataFrame(list(json.loads(result).values())[0])
|
|
df
|
|
``` |