from urllib.request import urlopen, Request
from bs4 import BeautifulSoup
import os
from urllib.request import urlretrieve
url = "http://cjc.ict.ac.cn/qwjs/No2020-01.htm"
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.105 Safari/537.36'}
ret = Request(url, headers=headers)
html = urlopen(ret)
bs = BeautifulSoup(html, "html.parser")
div = bs.find("div", {"class": "Section1"})
titles = div.find_all("span", {"style": "color:#006688"})
a_all = div.find_all("a")
i = 0
title_list = []
for title in titles:
title = title.get_text().encode('iso-8859-1').decode('gbk')
title_list.append(title)
for a in a_all:
href = a["href"]
if not os.path.exists('./Directory'):
os.makedirs('./Directory')
dir = os.path.abspath('./Directory')
work_path = os.path.join(dir, '{}.pdf').format(str(i + 1) + title_list[i])
urlretrieve(href, work_path)
i += 1
Python爬虫学习之爬取下载pdf文献
最新推荐文章于 2024-06-11 20:20:32 发布