Python网络爬虫与信息提取（中国大学mooc）

目录

Python网络爬虫与信息提取

1. 淘宝商品比价定向爬虫
2. 股票数据定向爬虫

1. 淘宝商品比价定向爬虫

---

功能描述

目标：获取淘宝搜索页面的信息

理解：淘宝的搜索接口翻页的处理

技术路线：requests-re[^footnote].

---

代码如下：

#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()

流程图：
步骤1：提交商品搜索请求，循环获取页面
步骤2：对于每个页面，提取商品名称和价格信息
步骤3：将信息输出到屏幕上

Created with Raphaël 2.1.0 开始 提交商品搜索请求，循环获取页面 对于每个页面，提取商品名称和价格信息 将信息输出到屏幕上 结束

2. 股票数据定向爬虫

---

1. 列表内容

功能描述
目标：获取上交所和深交所所有股票的名称和交易信息
输出：保存到文件中
技术路线：requests-bs4-re

新浪股票：http://finance.sina.com.cn/stock/
百度股票：https://gupiao.baidu.com/stock/

2.爬取网站原则

选取原则：股票信息静态存在于HTML页面中，非js代码生成，没有Robots协议限制
选取方法：浏览器F12，源代码查看等
选取心态：不要纠结于某个网站，多找信息源尝试

程序结构如下

Created with Raphaël 2.1.0 开始 步骤1：从东方财富网获取股票列表 步骤2：根据股票列表逐个到百度股票获取个股信息 步骤3：将结果存储到文件 结束

代码如下

#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' )
        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()

代码优化

1.编码识别优化
2.增加动态进度显示

优化后代码如下

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 = 'https://gupiao.baidu.com/stock/'
    output_file = 'D:/BaiduStockInfo.txt'
    slist=[]
    getStockList(slist, stock_list_url)
    getStockInfo(slist, stock_info_url, output_file)

main()

---

来自
Python网络爬虫与信息提取
中国大学mooc
http://www.icourse163.org/learn/BIT-1001870001?tid=1001962001#/learn/content?type=detail&id=1002699548&cid=1003101008