[Python3 Crawler from entry to Mastery] China big ... __python

#采用request-BS4 Route realizes Chinese University ranked Directional crawler # optimization of mixed-output problems in China and English import requests from BS4 import beautifulsoup import BS4 #import BS4 to use its Label type definition
def gethtmltext (URL): try:r = requests.get (URL, timeout =) # print (R.status_code) 200 is normal, all other information is incorrect R.raise_for_status () r.encoding = r.apparent_encoding return r.text except:return ' Get Faile D. '
def fillunivlist (ulist, HTML):     Soup =beautifulsoup (HTML, ' Html.parser ')     #print (soup[0:500)) Error: Typeerror:unhashable type: ' Slice '     for tr insoup.find (' tbody '). Children:        if ISI Nstance (TR, bs4.element.Tag):        # isinstance (object,classinfo) isinstance function to determine whether an object is an instance of a type        #tr有可能不是标签类型, here to determine the role of filtering            TDS =tr (' TD ')     &N bsp;      # put all TD tags into list TDS           # Print (tds[0]) output:    &NBSP ;      # Print (TDS)           ulist.append   ([Tds[0].string, Tds[1]. String, tds[3].string])            def printunivlist (ulist, num):     #tplt = ' {: ^10}\t{1:{3}^10}\t{:^10} ' ERROR: Valueerror:cannot switchfrom automatic field numbering to manual fieldspecification Sp   TPLT = ' {0:^10}\t{1:{3}^10}\T{2:^10} '     #其中0 indicates the first fill position, 1 the second, and so on     #: The character followed by the fill, can only be one character, not specified the default is to fill the     with a half-width space #p Rint (' {: ^10}\t{: ^6}\t{: ^10} '. Format (' rank ', ' School name ', ' Total Score '))//Error: Keyerror: '     #print ({: ^10}\t{:^6}\t{:^10} . Format (' rank ', ' School name ', ' total score ')     print (Tplt.format (' rank ', ' School name ', ' Total score ', Chr (12288)))     #chr (12288) Should be a full-width space     #一个汉字也只算一个字符     for i inrange (num):        u = ulist[i]        Print (Tplt.format (u[0], u[1], U[2],CHR (12288))
def main (): Uinfo = [] url = ' http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html ' html =gethtmltext (URL) Fillunivlist (uinfo,html) printunivlist (uinfo) # univ Main () B Station Learning connection: "Python web crawler and information extraction." Mooc. Beijing Institute