[已解决]一个简单的网页排名爬取，但是返回的内容是空的

CsY光子精灵

爬虫的目的是爬取http://www.zuihaodaxue.com/zuihaodaxuepaiming2019.html这个网页上的大学排名列表。但是返回的内容是空的。

import requests
from bs4 import BeautifulSoup
import bs4 

def getHTMLText(url):
    try:
        r = requests.get(url,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")
                         
    for tr in soup.find('tbody').children:
        if isinstance(tr,bs4.element.Tag):
            tds = tr('td')
            ulist.append([tds[0].string,tds[1].string,tds[2].string])
                         
    

def printUnivList(ulist,num):
    print("{:^10}\t{:^6}\t{:^10}".format("排名","学校名称","总分"))
    for i in range(num):
        u=ulist[i]
        print("{:^10}\t{:^6}\t{:^10}".format("u[0]","u[1]","u[2]"))
        
    

def  main():
    uinfo=[]
    url=" http://www.zuihaodaxue.com/zuihaodaxuepaiming2019.html"
    html = getHTMLText(url)
    fillUnivList(uinfo,html)
    printUnivList(uinfo,20)

main()

最佳答案

月排行榜 / 总排行榜

Twilight6

2020-4-30 17:49:27

import requests
from bs4 import BeautifulSoup
import bs4


def getHTMLText(url):
    try:
        r = requests.get(url, 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")

    for tr in soup.find('tbody').children:
        if isinstance(tr, bs4.element.Tag):
            tds = tr('td')
            ulist.append([tds[0].string, tds[1].string, tds[3].string])




def printUnivList(ulist, num):
    print("{:^10}\t{:^6}\t{:^10}".format("排名", "学校名称", "总分"))
    for i in range(num):
        u = ulist[i]
        print("{:^10}\t{:^10}\t{:^10}".format(u[0], u[1], u[2]))


def main():
    uinfo = []
    url = " http://www.zuihaodaxue.com/zuihaodaxuepaiming2019.html"
    html = getHTMLText(url)
    fillUnivList(uinfo, html)
    return printUnivList(uinfo, 20)


main()

都帮你改了下，就是总分那边不居中

跳转到最佳答案楼层

Twilight6

你没有设置函数的retuen吧 最后

def main():
    uinfo = []
    url = " http://www.zuihaodaxue.com/zuihaodaxuepaiming2019.html"
    html = getHTMLText(url)
    fillUnivList(uinfo, html)
    return printUnivList(uinfo, 20)

要retuen才有返回值

还有这

def printUnivList(ulist, num):
    print("{:^10}\t{:^6}\t{:^10}".format("排名", "学校名称", "总分"))
    for i in range(num):
        u = ulist[i]
        print("{:^10}\t{:^6}\t{:^10}".format(u[0], u[1], u[2]))

这里你把u[0], u[1], u[2],加上了引号应该去掉把

March2615

我这里显示是可以得到结果的
另外，你总分爬取写错了

Twilight6

import requests
from bs4 import BeautifulSoup
import bs4


def getHTMLText(url):
    try:
        r = requests.get(url, 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")

    for tr in soup.find('tbody').children:
        if isinstance(tr, bs4.element.Tag):
            tds = tr('td')
            ulist.append([tds[0].string, tds[1].string, tds[3].string])




def printUnivList(ulist, num):
    print("{:^10}\t{:^6}\t{:^10}".format("排名", "学校名称", "总分"))
    for i in range(num):
        u = ulist[i]
        print("{:^10}\t{:^10}\t{:^10}".format(u[0], u[1], u[2]))


def main():
    uinfo = []
    url = " http://www.zuihaodaxue.com/zuihaodaxuepaiming2019.html"
    html = getHTMLText(url)
    fillUnivList(uinfo, html)
    return printUnivList(uinfo, 20)


main()

都帮你改了下，就是总分那边不居中