Python网络爬虫之制作股票数据定向爬虫 以及爬取的优化 可以显示进度条！

版权声明：转载请声明原文链接地址，谢谢！ https://blog.csdn.net/weixin_42859280/article/details/84439168

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

选取原则：

1. 无robots协议
2. 非js网页
3. 数据在HTMLK页面中的

F12，查看源代码，即可查看。

新浪股票，使用JS制作。脚本生成的数据。

百度股票可以在HTML中查询到！

http://quote.eastmoney.com/stocklist.html

这个地址可以查询股票详细列表！

程序思路：

1. 获取股票列表
2. 根据列表信息到百度获取个股信息2，根据列表信息到百度获取个股信息
3. 将结果存储

考虑用字典作为数据容器进行存储！

火狐浏览器可以查看源代码，蓝色的IE浏览器就会出现乱码：
火狐的:

因为a标签，太多所以正则表达式匹配比较困难。
可用try except来解决！

[s]：表示s。[hz]：表示h z。后面是随意6个数。
SH:

SZ:

优化：

1. r.encoding:仅从头部获得
2. r.apparent_encoding:是从全文获得的。r.apparent_encoding:是从全文获得的。

优化就是将编码直接给代码，另外一个就是显示进度。

下面就是代码部分啦：

最初的代码：(真长)

import requests
from bs4 import BeautifulSoup
import traceback
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 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 = valurList[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 = 'https://quote.eastmoney.com/stocklist.html'
    stock_info_url = 'https://gupiao.baidu.com/stock/'
    output_file = 'D:\234.txt'
    slist = []
    getStockList(slist, stock_list_url)
    getStockInfo(slist, stock_info_url, output_file)

main()

代码执行结果;

优化后的代码：

import requests
from bs4 import BeautifulSoup
import traceback
import re

def getHTMLText(url,code='utf-8'):#默认的是utf-8
    try:
        r = requests.get(url, timeout = 30)
        r.raise_for_status()
        r.encoding = code#直接赋值
        return r.text
    except:
        return ""
def getStockList(lst, stockURL):
    html = getHTMLText(stockURL,'GB2312')#已经查询过啦！
    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 = valurList[i].text
                infoDict[key] = val

            with open(fpath, 'a', encoding='utf-8') as f:
                f.write(str(infoDict) + '\n')
                count = count +1
                print('\r当前速度：{:.2f}%'.format(count*100/len(lst)),end=' ')
        except:
            count = count +1
            print('\r当前速度：{:.2f}%'.format(count*100/len(lst)),end=' ')
            traceback.print_exc()
            continue
def main():
    stock_list_url = 'https://quote.eastmoney.com/stocklist.html'
    stock_info_url = 'https://gupiao.baidu.com/stock/'
    output_file = 'D:\234.txt'
    slist = []
    getStockList(slist, stock_list_url)
    getStockInfo(slist, stock_info_url, output_file)

main()

提前给出了编码方式以及可以显示进度条的代码
给出编码方式的代码：

def getHTMLText(url,code='utf-8'):#默认的是utf-8
    try:
        r = requests.get(url, timeout = 30)
        r.raise_for_status()
        r.encoding = code#直接赋值
        return r.text
    except:
        return ""
def getStockList(lst, stockURL):
    html = getHTMLText(stockURL,'GB2312')#已经查询过啦！
    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

照片：
（如果不是utf-8，就要提前给替换掉！）

可以显示进度条的代码

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 = valurList[i].text
                infoDict[key] = val

            with open(fpath, 'a', encoding='utf-8') as f:
                f.write(str(infoDict) + '\n')
                count = count +1
                print('\r当前速度：{:.2f}%'.format(count*100/len(lst)),end=' ')
        except:
            count = count +1
            print('\r当前速度：{:.2f}%'.format(count*100/len(lst)),end=' ')
            traceback.print_exc()
            continue

照片：
不过，显示进度在IDLE那里不可以显示。
但是最后我也没成功有文件生成以及显示进度条，算啦。先去吃饭啦~