淘宝商品与股票数据爬虫实战

在学过正则表达式后，跟着老师实战了下“淘宝商品比价定向爬虫”和“股票数据定向爬虫”这两个。

一开始我想了下，思路好迷糊，不好从哪下手。在看了老师的教程后，才慢慢的理解了。下面是代码与效果

淘宝商品比价定向爬虫：

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}	{:8}	{:16}"
    print(tplt.format("序号","价格","商品名称"))
    count = 0
    for g in ilt:
        count += 1
        print(tplt.format(count, g[0], g[1]))

def main():
    goods = 'acm'
    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()

下面是效果：

 股票数据定向爬虫：

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")#由于知道网站编码,就可以直接赋值进去，如果用r.status_encoding的话时间更久些
    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) + '
' )
                count = count + 1
                print("
当前进度: {:.2f}%".format(count*100/len(lst)),end="")
        except:
            count = count + 1
            print("
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 = 'https://gupiao.baidu.com/stock/'
    output_file = 'E:/BaiduStockInfo.txt'
    slist=[]
    getStockList(slist, stock_list_url)
    getStockInfo(slist, stock_info_url, output_file)
 
main()

效果的话先放这个吧，爬取时间有点慢