def get_pdf(html):
""" xxx"""
reg = r'href="(.+?\.pdf)">pdf'
pdfre = re.compile(reg)
pdflist = re.findall(pdfre, html)
dir_name = 'CVPR2015'
maxrows = len(pdflist)
pbar = prgbar.ProgressBar(total=maxrows)
if os.path.exists(dir_name) is False:
os.mkdir(dir_name)
for idx, pdfurl in enumerate(pdflist):
reg2 = r'papers/(.+?\.pdf)'
pdfre2 = re.compile(reg2)
filename = dir_name + '/' + re.findall(pdfre2, pdfurl)[0]
pbar.log('http://www.cv-foundation.org/openaccess/' + pdfurl)
if os.path.exists(filename) is True:
pbar.log('Exist')
else:
urllib.urlretrieve(
'http://www.cv-foundation.org/openaccess/' + pdfurl, filename)
pbar.update(index=(idx + 1))
pbar.finish()
def get_pdf(html, keywords):
""" xxx"""
reg = r'href="(.+?\.pdf)">pdf'
pdfre = re.compile(reg)
pdflist = re.findall(pdfre, html)
dir_name = 'CVPR2018'
maxrows = len(pdflist)
pbar = prgbar.ProgressBar(total=maxrows)
if os.path.exists(dir_name) is False:
os.mkdir(dir_name)
for idx, pdfurl in enumerate(pdflist):
reg2 = r'papers/(.+?\.pdf)'
pdfre2 = re.compile(reg2)
name_ori = re.findall(pdfre2, pdfurl)[0]
# words list
words_list = name_ori.split('_')
name_list = words_list[1:-3]
filename = dir_name + '/' + contrust_paper_name(name_list)
print(filename)
pbar.log('http://openaccess.thecvf.com/' + pdfurl)
if os.path.exists(filename) is True:
pbar.log('Exist')
else:
urllib.urlretrieve(
'http://openaccess.thecvf.com/' + pdfurl, filename)
# # ingore unconcerned papers
# if keywords in name_list:
# filename = dir_name + '/' + contrust_paper_name(name_list)
# print(filename)
# pbar.log('http://openaccess.thecvf.com/' + pdfurl)
# if os.path.exists(filename) is True:
# pbar.log('Exist')
# else:
# urllib.urlretrieve(
# 'http://openaccess.thecvf.com/' + pdfurl, filename)
# else:
# print('ignore paper %s' % name_ori)
pbar.update(index=(idx + 1))
pbar.finish()
def get_pdf(html):
""" xxx"""
reg = r'href="(.+?\.pdf)">pdf'
pdfre = re.compile(reg)
pdflist = re.findall(pdfre, html)
dir_name = 'COLT2016'
if os.path.exists(dir_name) is False:
os.mkdir(dir_name)
maxrows = len(pdflist)
pbar = prgbar.ProgressBar(total=maxrows)
for idx, pdfurl in enumerate(pdflist):
filename = dir_name + '/' + pdfurl
pbar.log('http://jmlr.org/proceedings/papers/v49/' + pdfurl)
if os.path.exists(filename) is True:
pbar.log('Exist')
else:
urllib.urlretrieve(
'http://jmlr.org/proceedings/papers/v49/' + pdfurl, filename)
pbar.update(index=(idx + 1))
pbar.finish()
def get_pdf(html):
""" xxx"""
reg = r'href="/paper/(.+?)"'
pdfre = re.compile(reg)
pdflist = re.findall(pdfre, html)
dir_name = 'NIPS2014'
maxrows = len(pdflist)
pbar = prgbar.ProgressBar(total=maxrows)
if os.path.exists(dir_name) is False:
os.mkdir(dir_name)
for idx, pdfurl in enumerate(pdflist):
filename = dir_name + '/' + pdfurl + '.pdf'
pbar.log('http://papers.nips.cc/paper/' + pdfurl + '.pdf')
if os.path.exists(filename) is True:
pbar.log('Exist')
else:
urllib.urlretrieve(
'http://papers.nips.cc/paper/' + pdfurl + '.pdf', filename)
pbar.update(index=(idx + 1))
pbar.finish()
