ISTDSA_DS_Bootcamp_Project2_WebScraping_Regression_P2

getPageLinks.py

PAGE_LINKS = []
def getPageLinks(url) :
    html = getAndParseURL(url)
    for i in html.findAll("link",{"rel":"canonical"}) :
        for b in range(1,51) :
            PAGE_LINKS.append(url + "?page={}".format(b))
    return PAGE_LINKS