guanjihuan/guanjihuan.com
1
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update download_references_in_a_pdf_file_with_python.py

Browse Source
This commit is contained in:
guanjihuan 2022-06-29 17:25:40 +08:00
parent 23be72b2c1
commit 6d04f423aa
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
language_learning/2020.10.31_download_references_in_a_pdf_file_with_python/download_references_in_a_pdf_file_with_python.py
View File

@ -55,7 +55,8 @@ def download(links):
print('\n响应结果是：', r) print('\n响应结果是：', r)
print('访问的地址是：', r.url) print('访问的地址是：', r.url)
soup = BeautifulSoup(r.text, features='lxml') soup = BeautifulSoup(r.text, features='lxml')
pdf_URL = soup.iframe['src'] pdf_URL = soup.embed['src']
# pdf_URL = soup.iframe['src'] # This is a code line of history version which fails to get pdf URL.
if re.search(re.compile('^https:'), pdf_URL): if re.search(re.compile('^https:'), pdf_URL):
pass pass
else: else: