python爬虫第六节：“中国大学排名”定向爬虫

功能描述：
1.输入：大学排名的 URL 链接
2.输出：大学排名信息的品目输出（排名，大学名称，总分）
3.定向爬虫：仅对输入 URL 进行爬取，不扩展爬取其他 URL
http://www.zuihaodaxue.com/robots.txt 查看robots协议：发现404 ，说明没有爬取限制

# 实现步骤：

 

# Code：
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):# 新引入bs4
            tds = tr('td')
            ulist.append([tds[0].string, tds[1].string, tds[2].string]) # 新增字段：大学排名、名字、分数

def printUnivList(ulist,num):
    print( "{:^10}\t{:^6}\t{:^10}".format("排名","学校","分数") )
    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) # 20 univs

main()


# 优化：实现文本对齐，采用中文字符的空格chr(12288) 填充
def printUnivList2(ulist,num):
    tplt = "{0:^10}\t{1:{3}^10}\t{2:^10}"
    print( tplt.format("排名","学校","分数",chr(12288)))
    for i in range(num):
        u = ulist[i]
        print( tplt.format(u[0],u[1],u[2],chr(12288)) )
        

 

# 改进：
import requests
import re
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):# 新引入bs4
            tds = tr('td')
            ulist.append([tds[0].string, tds[1].string, tds[2].string, tds[3].string]) # 新增字段：大学排名、名字、省份、分数

def printUnivList(ulist,num):
    print( "{:^8}\t{:^16}\t{:^10}\t{:^9}".format("排名","学校","省份","分数",chr(12288))) # 在IDE里面显示总是调不出对齐，writeTxt里面可以对齐
    for i in range(num):
        u = ulist[i]
        print( "{:^8}\t{:^14}\t{:^10}\t{:^10}".format(u[0],u[1],u[2],u[3],chr(12288)))


def writeTxt(ulist,num):
    fb = open('中国大学排名.txt', 'w', encoding='utf-8')
    fb.write( "{:^8}\t{:^16}\t{:^10}\t{:^9}".format("排名","学校","省份","分数",chr(12288)) + '\n')# 间距经过不断调试最终确定
    for i in range(num):
        u = ulist[i]
        fb.write("{:^8}\t{:^14}\t{:^10}\t{:^10}".format(u[0],u[1],u[2],u[3],chr(12288))  + '\n')
    fb.close()

def main():
    uinfo = []
    url = "http://www.zuihaodaxue.com/zuihaodaxuepaiming2019.html"
    html = getHTMLText(url)
    fillUnivList(uinfo,html)
    printUnivList(uinfo,30)  # IDE 打印
    writeTxt(uinfo,30)       # 写入文件
    
main()