第三周 淘宝商品/股票数据定向爬虫

浏览器打开淘宝，搜索“书包”

第一页链接：https://s.taobao.com/search?q=书包&imgfile=&commend=all&ssid=s5-e&search_type=item&sourceId=tb.index&spm=&ie=utf8&initiative_id=tbindexz_20170306

第二页链接：https://s.taobao.com/search?q=书包&imgfile=&js=1&stats_click=search_radio_all%3A1&initiative_id=staobaoz_20180713&ie=utf8&bcoffset=3&ntoffset=3&p4ppushleft=1%2C48&s=44

第三页链接：https://s.taobao.com/search?q=书包&imgfile=&js=1&stats_click=search_radio_all%3A1&initiative_id=staobaoz_20180713&ie=utf8&bcoffset=0&ntoffset=6&p4ppushleft=1%2C48&s=88

 

观察链接可以看出每页商品有44个

import requests
import re

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

     
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 = '电脑'
    depth = 2
    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()

 股票数据：

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:
            traceback.print_exc()
            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()