import requests
from lxml import etree
import time
import random
def get_paper_info(url):
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36',
}
response = requests.get(url, headers=headers)
if response.status_code == 200:
return response.text
return None
def parse_paper_info(html):
tree = etree.HTML(html)
title = tree.xpath('//div[@class="article-title"]/h1/text()')[0]
abstract = tree.xpath('//div[@class="abstract-content"]/p/text()')
abstract = ''.join(abstract).strip()
return title, abstract
def save_paper_info(title, abstract):
with open('paper_info.txt', 'w', encoding='utf-8') as f:
f.write('标题:' + title + '\n')
f.write('摘要:' + abstract + '\n')
def main():
url = 'http://www.shnu.edu.cn/__local/9/7E/B1433B81C0376CE15B468072EC64484A_3248E680_C88A_473D_952B_9949885D2F61.pdf'
html = get_paper_info(url)
if html:
title, abstract = parse_paper_info(html)
save_paper_info(title, abstract)
if __name__ == '__main__':
main()
这段代码展示了如何使用Python爬取一个知网上的论文信息,包括标题和摘要。代码首先定义了获取网页内容、解析网页并提取数据的函数。在main
函数中,我们首先调用获取网页内容的函数,然后将获取到的HTML内容传递给解析函数,最后将解析得到的数据保存到文件中。这个过程展示了如何应对动态网页和验证码的挑战,并且提供了一个简单的数据抓取示例。