爬虫脚本实例

1.中国大学排名

#CrawUnivRankingB.py
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):
    tplt = "{0:^10}\t{1:{3}^10}\t{2:^10}"
    print(tplt.format("排名","学校名称","总分",chr(12288)))
    for i in range(num):
        u=ulist[i]
        print(tplt.format(u[0],u[1],u[2],chr(12288)))
     
def main():
    uinfo = []
    url = 'http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html'
    html = getHTMLText(url)
    fillUnivList(uinfo, html)
    printUnivList(uinfo, 20) # 20 univs
main()

 

2.淘宝商品

#CrowTaobaoPrice.py
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 = 'http://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()

 

 

3.亚马逊商品

#CrawBaiduStocksB.py
import requests
from bs4 import BeautifulSoup
import traceback
import re
 
def getHTMLText(url, code="utf-8"):
    try:
        r = requests.get(url)
        r.raise_for_status()
        r.encoding = code
        return r.text
    except:
        return ""
 
def getStockList(lst, stockURL):
    html = getHTMLText(stockURL, "GB2312")
    soup = BeautifulSoup(html, 'html.parser') 
    a = soup.find_all('a')
    for i in a:
        try:
            href = i.attrs['href']
            lst.append(re.findall(r"[s][hz]\d{6}", href)[0])
        except:
            continue
 
def getStockInfo(lst, stockURL, fpath):
    count = 0
    for stock in lst:
        url = stockURL + stock + ".html"
        html = getHTMLText(url)
        try:
            if html=="":
                continue
            infoDict = {}
            soup = BeautifulSoup(html, 'html.parser')
            stockInfo = soup.find('div',attrs={'class':'stock-bets'})
 
            name = stockInfo.find_all(attrs={'class':'bets-name'})[0]
            infoDict.update({'股票名称': name.text.split()[0]})
             
            keyList = stockInfo.find_all('dt')
            valueList = stockInfo.find_all('dd')
            for i in range(len(keyList)):
                key = keyList[i].text
                val = valueList[i].text
                infoDict[key] = val
             
            with open(fpath, 'a', encoding='utf-8') as f:
                f.write( str(infoDict) + '\n' )
                count = count + 1
                print("\r当前进度: {:.2f}%".format(count*100/len(lst)),end="")
        except:
            count = count + 1
            print("\r当前进度: {:.2f}%".format(count*100/len(lst)),end="")
            continue
 
def main():
    stock_list_url = 'http://quote.eastmoney.com/stocklist.html'
    stock_info_url = 'http://gupiao.baidu.com/stock/'
    output_file = 'D:/BaiduStockInfo.txt'
    slist=[]
    getStockList(slist, stock_list_url)
    getStockInfo(slist, stock_info_url, output_file)
 
main()