网页爬取

1、图片爬取代码

import requests
import os

root = "H:/美图/"
url = "https://k.zol-img.com.cn/sjbbs/7692/a7691501_s.jpg"
path = root + url.split("/")[-1]
try:
    if not os.path.exists(root):
        os.mkdir(root)
    if not os.path.exists(path):
        r = requests.get(url)
        r.raise_for_status()
        with open(path, "wb") as f:
            f.write(r.content)
            f.close()
            print("文件保存成功")
    else:
        print("文件已经存在")
except:
    print("爬取失败")

 2.打印大学排名

import requests
from bs4 import BeautifulSoup
import bs4


def getHTMLText(url):
    try:
        r = requests.get(url)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return ""


def parserHTML(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("{0:^10}\t{1:{3}^8}\t{2:^8}".format("排名","学校","总分",chr(12288)))
    for i in range(num):
        print("{0:^10}\t{1:{3}^10}\t{2:^10}".format(ulist[i][0],ulist[i][1],ulist[i][2],chr(12288)))

def main():
    url = "http://www.zuihaodaxue.com/zuihaodaxuepaiming2016.html"
    html = getHTMLText(url)
    ulist = []
    parserHTML(ulist,html)
    printUnivList(ulist,10)

main()

打印大学列表时，使用format（）函数时，注意填充的字符是中文还是英文字符，使用chr(12288)填充中文字符