sciencedirect_collect.py 文件源码

def getJournalURL(jname):
# get journal URL given the journal name for retrieving article PIIs
    urlstr = "http://api.elsevier.com/sitemap/page/sitemap/" + jname[0].lower() + ".html"
    retl = ""
    with urllib.request.urlopen(urlstr) as url:
        response = url.read()
        linkcnt = 0
        for link in BeautifulSoup(response, parse_only=SoupStrainer("a")):
            if linkcnt == 0:
                linkcnt += 1
                continue
            if link.has_attr("href"):
                if link.text.lower() == jname.lower():
                    #print(link["href"])
                    retl = link["href"]
                    break
            linkcnt += 1
    return retl