《python网络爬虫与信息提取》学习笔记（三）

信息标记的三种形式及区别

1、XML


2、JSON



3、YAML

信息提取的一般方法

获取HTML页面中所包含的链接内容

基于bs4库的HTML内容查找方法

"中国大学排名定向爬虫"实例

实例编写：

import bs4
import requests
from bs4 import BeautifulSoup


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(uast, html):
    soup = BeautifulSoup(html, "html.parser")
    for tr in soup.find('tbody').children:
        if isinstance(tr, bs4.element.Tag):
            tds = tr('td')
            uast.append([tds[0].string, tds[1].string, tds[2].string])


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


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


main()

实例优化：
当中文字符宽度不够时，系统默认采用西文字符填充，存在中文输出对齐问题
采用中文字符的空格填充chr(12288)

import bs4
import requests
from bs4 import BeautifulSoup


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


def printUnivList(ugliest, num):
    print("{0:^10}\t{1:{3}^10}\t{2:^10}".format("排名", "学校名称", "总分", chr(12288)))
    for i in range(num):
        u = ugliest[i]
        print("{0:^10}\t{1:{3}^10}\t{2:^10}".format(u[0], u[1], u[2], chr(12288)))


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


main()