sciencedirect_collect.py 文件源码

def collectArticles(urlstr):
# get article PIIs
    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"):
                #print(link["href"])
                retl.append(link["href"])
            linkcnt += 1
    return retl