python网络爬虫代码

同步跟着mooc学习，写了爬取淘宝的代码

import requests
import re
 
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 parsePage(ilt, html):
    try:
        plt = re.findall(r'\"view_price\"\:\"[\d\.]*\"',html)
        tlt = re.findall(r'\"raw_title\"\:\".*?\"',html)
        for i in range(len(plt)):
            price = eval(plt[i].split(':')[1])
            title = eval(tlt[i].split(':')[1])
            ilt.append([price , title])
    except:
        print("")
 
def printGoodsList(ilt):
    tplt = "{:4}\t{:8}\t{:16}"
    print(tplt.format("序号", "价格", "商品名称"))
    count = 0
    for g in ilt:
        count = count + 1
        print(tplt.format(count, g[0], g[1]))
         
def main():
    goods = '书包'
    depth = 3
    start_url = 'https://s.taobao.com/search?q=' + goods
    infoList = []
    for i in range(depth):
        try:
            url = start_url + '&s=' + str(44*i)
            html = getHTMLText(url)
            parsePage(infoList, html)
        except:
            continue
    printGoodsList(infoList)
     
main()

大学排名的爬虫

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 ""
    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([td[0].string,td[1].string,td[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{:10}".format(u[0],u[1],u[2]))
def main():
    uinfo = []
    url='http://www.icourse163.org/learn/BIT-1001870001?tid=1001962001#/learn/content?type=detail&id=1002702163&cid=1003077347&replay=true'
    html = getHTMLText(url)
    fillUnivList(uinfo,html)
    printUnivList(uinfo,20)
main()