爬取中国大学排名实例
import requests from bs4 import BeautifulSoup import bs4 import re def getHTMLText(url): try: kv = {"user-agent":"Mozilla/5.0"} r = requests.get(url,headers=kv,timeout=30) r.raise_for_status() r.encoding = r.apparent_encoding return r.text except: return "" def fillUnivList(ulist,html): soup = BeautifulSoup(html,'html.parser') tbody = soup.find('tbody') for tr in soup.find('tbody').children: if isinstance(tr, bs4.element.Tag): tds = tr.find_all('td') #print(tds) # st0 = getTagText(str(tds[0])) st0 = re.sub(r"<!--.*-->", "", str(tds[0])) st0 = re.sub(r"</td>","",st0) st0 = re.sub(r"<.*>","",st0) st0 = re.sub(r" ","",st0) st0 = re.sub("\n","",st0) #st1 = getTagText(str(tds[1])) aas =tds[1].find_all('a') st1 = aas[0].string st1 = re.sub(r" ","",st1) st1 = re.sub("\n","",st1) #st4 = getTagText(str(tds[4])) st4 = re.sub(r"<!--.*-->", "", str(tds[4])) st4 = re.sub(r"</td>","",st4) st4 = re.sub(r"<.*>","",st4) st4 = re.sub(r" ","",st4) st4 = re.sub("\n","",st4) #print(st0,end = ",") #print(st1,end = ",") #print(st4,end = ",") #print(tds[1]) #st0 = re.sub(r"<.*>","",str(tds[0])) #st1 = re.sub(r"<.*>","",str(tds[1])) #st4 = re.sub(r"<.*>","",str(tds[4])) #print(st0) #print(st1) #print(st4) ulist.append([st0 , st1 , st4 ] ) ###!!!!!!!!出错 def printUnivList(ulist,num): tplt = "{0:^10}\t{1:{3}^10}\t{2:^10}" #详情去看.format的用法 print(tplt.format("排名","学校名称","总分",chr(12288))) for i in range(num): u=ulist[i] print(tplt.format(u[0],u[1],u[2],chr(12288))) def main(): uinfo = [] url = "https://www.shanghairanking.cn/rankings/bcur/2020" html = getHTMLText(url) fillUnivList(uinfo,html) printUnivList(uinfo, 20) main()
其中与慕课上稍有变动,由于在td标签中加入了,因此不能直接用.string获得标签中的信息,所以将标签转化为字符串类型,然后运用re.sub()将字符串进行处理,最后得到所需要的结果。