利用大型语言模型增强网络抓取：现代方法

from bs4 import BeautifulSoup
import requests


def extract_html_from_url(url):
    try:
        # 使用requests从URL获取HTML内容
        response = requests.get(url)
        response.raise_for_status()  # Raise an exception for bad responses (4xx and 5xx)

        # 使用BeautifulSoup解析HTML内容
        soup = BeautifulSoup(response.content, "html.parser")
        excluded_tagNames = ["footer", "nav"]
        # 排除标签名为'footer'和'nav'的元素
        for tag_name in excluded_tagNames:
            for unwanted_tag in soup.find_all(tag_name):
                unwanted_tag.extract()

        # 处理soup以保留锚点标签中的href属性
        for a_tag in soup.find_all("a"):
            href = a_tag.get("href")
            if href:
                a_tag.string = f"{a_tag.get_text()} ({href})"

        return ' '.join(soup.stripped_strings)  # Return text content with preserved hrefs

    except requests.exceptions.RequestException as e:
        print(f"Error fetching data from {url}: {e}")
        return None

from pydantic import BaseModel, Field
from typing import Optional

class Activity(BaseModel):
    title: str = Field(description="The title of the activity.")
    rating: float = Field(description="The average user rating out of 10.")
    reviews_count: int = Field(description="The total number of reviews received.")
    travelers_count: Optional[int] = Field(description="The number of travelers who have participated.")
    cancellation_policy: Optional[str] = Field(description="The cancellation policy for the activity.")
    description: str = Field(description="A detailed description of what the activity entails.")
    duration: str = Field(description="The duration of the activity, usually given in hours or days.")
    language: Optional[str] = Field(description="The primary language in which the activity is conducted.")
    category: str = Field(description="The category of the activity, such as 'Boat Trip', 'City Tours', etc.")
    price: float = Field(description="The price of the activity.")
    currency: str = Field(description="The currency in which the price is denominated, such as USD, EUR, GBP, etc.")

    
class ActivityScrapper(BaseModel):
    Activities: list[Activity] = Field("List of all the activities listed in the text")

from langchain.prompts import PromptTemplate
from langchain.output_parsers import PydanticOutputParser
from langchain_openai import ChatOpenAI
from dotenv import load_dotenv

load_dotenv()

llm = ChatOpenAI(temperature=0)
output_parser = PydanticOutputParser(pydantic_object = ActivityScrapper)

prompt_template = """
You are an expert making web scrapping and analyzing HTML raw code.
If there is no explicit information don't make any assumption.
Extract all objects that matched the instructions from the following html
{html_text}
Provide them in a list, also if there is a next page link remember to add it to the object.
Please, follow carefulling the following instructions
{format_instructions}
"""

prompt = PromptTemplate(
    template=prompt_template,
    input_variables=["html_text"],
    partial_variables={"format_instructions": output_parser.get_format_instructions}
)

chain = prompt | llm | output_parser

url = "https://www.civitatis.com/es/budapest/"
html_text_parsed = extract_html_from_url(url)
activites = chain.invoke(input={
    "html_text": html_text_parsed
})
activites.Activities