python批量下载pdf
# coding = UTF-8
# 爬取2022美赛证书pdf
import urllib.request
import re
import os
# open the url and read
def getHtml(url):
page = urllib.request.urlopen(url)
html = page.read()
page.close()
return html
def getFile(url):
file_name = url.split('/')[-1]
try:
u = urllib.request.urlopen(url)
except urllib.error.HTTPError:
# 碰到了匹配但不存在的文件时，提示并返回
print(url, "url file not found")
return
block_sz = 8192
with open(file_name, 'wb') as f:
while True:
buffer = u.read(block_sz)
if buffer:
f.write(buffer)
else:
break
print("Sucessful to download" + " " + file_name)
root_url = '/mcm/2022Certs/' # 下载地址中相同的部分
if not os.path.exists('pdf_download'):
# 文件夹不存在时，再进行创建
os.mkdir('pdf_download')
os.chdir(os.path.join(os.getcwd(), 'pdf_download'))
for url in range(2202950,2202955): # 任意给出控制号的范围，也可以根据自己单位的队伍号建立一个list
url = root_url + str(url) + '.pdf' # 形成完整的下载地址
getFile(url)