用于抓取文章的代码，爬取时报错，请解决

Question

import requests
from bs4 import BeautifulSoup

def search_pubmed(query):
    base_url = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/"
    search_url = base_url + "esearch.fcgi?db=pubmed&term=" + query
    response = requests.get(search_url)
    soup = BeautifulSoup(response.text, '')
    id_list = [id.text for id in soup.find_all('Id')]
    return id_list

def fetch_details(pubmed_id):
    base_url = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/"
    fetch_url = base_url + "efetch.fcgi?db=pubmed&id=" + pubmed_id + "&retmode=xml"
    response = requests.get(fetch_url)
    soup = BeautifulSoup(r.text, 'html.parser')
    soup = BeautifulSoup(response.text, 'xml')
    try:
        title = soup.find('ArticleTitle').text
    except AttributeError:
        title = None
    try:
        abstract = soup.find('AbstractText').text
    except AttributeError:
        abstract = None
    try:
        journal = soup.find('JournalTitle').text
    except AttributeError:
        journal = None
    try:
        doi = soup.find('ArticleId', {'IdType': 'doi'}).text
    except AttributeError:
        doi = None
    return {'title': title, 'abstract': abstract, 'journal': journal, 'doi': doi}

# Example usage
ids = search_pubmed('human')
for id in ids:
    details = fetch_details(id)
    print(details)
报错如下；
Traceback (most recent call last):
  File "F:/桌面/抓2.py", line 38, in <module>
    ids = search_pubmed('human')
  File "F:/桌面/抓2.py", line 9, in search_pubmed
    soup = BeautifulSoup(response.text, '')
  File "C:\Users\HUAWEI\AppData\Local\Programs\Python\Python311\Lib\site-packages\bs4\__init__.py", line 249, in __init__
    raise FeatureNotFound(
bs4.FeatureNotFound: Couldn't find a tree builder with the features you requested: . Do you need to install a parser library?

已经安装1xlm仍然报错，求解

Answer 1

代码 存在问题，已经帮你修改好了，下面的代码能够正常运行。
如果对你有帮助，点个采纳谢谢！

# !/usr/bin/env python
# -*- coding: utf-8 -*-

# @author: yjp
# @software: PyCharm
# @file: main.py
# @time: 2022-08-08 16:49
import requests
from bs4 import BeautifulSoup


def search_pubmed(query):
    base_url = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/"
    search_url = base_url + "esearch.fcgi?db=pubmed&term=" + query
    print(search_url)
    response = requests.get(search_url)
    soup = BeautifulSoup(response.text, 'xml')
    id_list = [id.text for id in soup.find_all('Id')]
    print(id_list)
    return id_list


def fetch_details(pubmed_id):
    base_url = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/"
    fetch_url = base_url + "efetch.fcgi?db=pubmed&id=" + pubmed_id + "&retmode=xml"
    print(fetch_url)
    response = requests.get(fetch_url)
    soup = BeautifulSoup(response.text, 'xml')
    try:
        title = soup.find('ArticleTitle').text
    except AttributeError:
        title = None
    try:
        abstract = soup.find('AbstractText').text
    except AttributeError:
        abstract = None
    try:
        journal = soup.find('JournalTitle').text
    except AttributeError:
        journal = None
    try:
        doi = soup.find('ArticleId', {'IdType': 'doi'}).text
    except AttributeError:
        doi = None
    return {'title': title, 'abstract': abstract, 'journal': journal, 'doi': doi}


if __name__ == '__main__':
    # Example usage
    ids = search_pubmed('human')
    for id in ids:
        details = fetch_details(id)
        print(details)