目錄

Python網路爬蟲與資訊提取

1. 淘寶商品比價定向爬蟲
2. 股票資料定向爬蟲

1. 淘寶商品比價定向爬蟲

功能描述

目標：獲取淘寶搜尋頁面的資訊

理解：淘寶的搜尋介面翻頁的處理

技術路線：requests-re[^footnote].

程式碼如下：

#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("序號", "價格", "商品名稱"))
    count = 0
    for g in ilt:
        count = count + 1
        print(tplt.format(count, g[0], g[1]))

def main():
    goods = '書包'
 

    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()

流程圖：
步驟1：提交商品搜尋請求，迴圈獲取頁面
步驟2：對於每個頁面，提取商品名稱和價格資訊
步驟3：將資訊輸出到螢幕上

2. 股票資料定向爬蟲

1. 列表內容

功能描述
目標：獲取上交所和深交所所有股票的名稱和交易資訊
輸出：儲存到檔案中
技術路線：requests-bs4-re

2.爬取網站原則

選取原則：股票資訊靜態存在於HTML頁面中，非js程式碼生成，沒有Robots協議限制
選取方法：瀏覽器F12，原始碼檢視等
選取心態：不要糾結於某個網站，多找資訊源嘗試

程式結構如下

程式碼如下

#CrawBaiduStocksA.py
import requests
from bs4 import BeautifulSoup
import traceback
import re

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

def getStockList(lst, stockURL):
    html = getHTMLText(stockURL)
    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):
    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({'股票名稱': 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' )
        except:
            traceback.print_exc()
            continue

def main():
    stock_list_url = 'http://quote.eastmoney.com/stocklist.html'
    stock_info_url = 'https://gupiao.baidu.com/stock/'
    output_file = 'D:/BaiduStockInfo.txt'
    slist=[]
    getStockList(slist, stock_list_url)
    getStockInfo(slist, stock_info_url, output_file)

main()

程式碼優化

1.編碼識別優化
2.增加動態進度顯示

優化後代碼如下

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({'股票名稱': 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當前進度: {:.2f}%".format(count*100/len(lst)),end="")
        except:
            count = count + 1
            print("\r當前進度: {:.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 = 'D:/BaiduStockInfo.txt'
    slist=[]
    getStockList(slist, stock_list_url)
    getStockInfo(slist, stock_info_url, output_file)

main()