python爬取万方数据库,python下载万方数据库文献

获取下载的链接的url

def getdownurl(url):

text=get_html(url).text

re0=r'

firurl=re.findall(re0,text)

print(firurl)

if len(firurl)==0:

return

strurl=str(firurl[0])

print(strurl)

tpurl=re.split(',',strurl)

endstp=[]

#print(tpurl)

for ul in tpurl:

elem=ul.strip('\'').strip('\'')

endstp.append(elem)

print(endstp,type(endstp[0]))

head='http://www.wanfangdata.com.cn/search/downLoad.do?page_cnt='

geturl=head+endstp[0]+"&language="+endstp[2]+"&resourceType="+endstp[6]+"&source="+endstp[3]+ "&resourceId="+endstp[1]+"&resourceTitle="+endstp[4]+"&isoa="+endstp[5]+"&type="+endstp[0]

print(geturl)

re1=r''

text=get_html(geturl).text

print()

sucurl=re.findall(re1,text)

print(sucurl)

return sucurl[0]

下载所有的ＰＤＦ文件

def downloadAllPdf(key):

row=getNum(key)

pages=search_key(key)

allurl=[]

num=0

for page in pages:

allurl=get_url(page)