12345

#问题2解决方案两个：# 1. 打开文件的时候就指定编码的类型    f = open('E:/Data.txt', 'r',encoding = 'utf-8')    f.read()# 2. 修改文件编码为utf-8

1

f.close()

123456

try:    f = open('E:/Data.txt', 'r', encoding = 'utf-8')    print(f.read())finally:    if f:        f.close()

12

with open('E:/Data.txt', 'r', encoding = 'utf-8') as f:    print(f.read())

12

with open('D:/20171226101748.png', 'rb') as f:    f.read()

1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162

from urllib import requestfrom bs4 import BeautifulSoup as bsimport re

def getCodes():    url = 'http://quote.eastmoney.com/stocklist.html';    resp = request.urlopen(url)    resp_text = resp.read().decode('gbk')    soap = bs(resp_text, 'html.parser')    list = soap.find_all('div', id = 'quotesearch')[0].find_all('ul')[0].find_all('li')

    codeList = []    for li in list:        try:             #eg: sh603183            codeList.append(re.findall(r"[s][hz]\d{6}", li.find('a')['href']))        except:            continue

    return codeList

def makeDict(code):    infoDict = {}    url = 'https://gupiao.baidu.com/stock/'+ code +'.html';    resp = request.urlopen(url)    resp_text = resp.read().decode('utf-8')    soap = bs(resp_text, 'html.parser')

    try:        stockInfo = soap.find_all(attrs = {'class','stock-bets'})        name = soap.find(attrs = {'class', 'bets-name'})        if name is None:            return None        infoDict['name'] = name.text.strip()        keys = soap.find_all('dt')        values = soap.find_all('dd')        for i in range(len(keys)):            infoDict[keys[i].text] = values[i].text

        return infoDict    except:        return None

def writeFile(codeList):    i=0    for code in codeList:        i = i+1        # 下面两个判断是因为前45个股票百度并没有信息，所以跳过了，200个以后的数据就不再取了，太多了，科科        if i < 45:            continue        if i > 200:            break        infoDict = makeDict(code[0])        if infoDict is None:            continue        print (infoDict)        with open('E://Data.txt', 'a', encoding = 'utf-8') as f:            f.write(str(infoDict) + '\n')

codeList = getCodes();print("start")writeFile(codeList)

12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667

# -*- coding: utf-8 -*-

import requestsfrom bs4 import BeautifulSoupimport tracebackimport 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):    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()