爬取到2020年所有论文标题
代码：
1 import re
2 import requests
3 from bs4 import BeautifulSoup
4 import lxml
5 import traceback
6 import time
7 import json
8 from lxml import etree
9 def get_paper():
10 #https://www.ecva.net/papers/eccv_2020/papers_ECCV/html/267_ECCV_2020_paper.php
11 #https://www.ecva.net/papers/eccv_2020/papers_ECCV/html/283_ECCV_2020_paper.php
12 #https://www.ecva.net/papers/eccv_2020/papers_ECCV/html/343_ECCV_2020_paper.php
13 url='https://www.ecva.net/papers.php'
14 headers = {
15 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.212 Safari/537.36'
16 }
17 response=requests.get(url,headers)
18 response.encoding='utf-8'
19 page_text=response.text
20 #输出页面html
21 # print(page_text)
22 soup = BeautifulSoup(page_text,'lxml')
23 all_dt=soup.find_all('dt',class_='ptitle')
24 for dt in all_dt:
25 single_dt=str(dt)
26 single_soup=BeautifulSoup(single_dt,'lxml')
27 title=single_soup.find('a').text
28 print(title)
29 return
30 if (__name__=='__main__'):
31 get_paper()
