1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253

import requests
import re
from lxml import etree
import pandas as pd
import time


StockPriceUrl = "http://money.finance.sina.com.cn/corp/go.php/vMS_MarketHistory/stockid/#code.phtml?year=#year&jidu=#jd"
StockListUrl = "http://quote.eastmoney.com/stocklist.html"
StockInfoUrl = 'https://gupiao.baidu.com/stock/'
StockListDataFile = "StockList.dat"
StockDictDataFile = "StockDict.dat"
StockDataFile = "StockInfo.dat"
StockGDData = "StockGD.dat"
StockGDUrl = "http://vip.stock.finance.sina.com.cn/corp/go.php/vCI_CirculateStockHolder/stockid/#code.phtml"
GDDataFile = "GDData.dat"
stockdict={}
StockList=[]

df = pd.DataFrame(columns=  ['date', 'code', 'name', 'no.',"price", 'cop', 'total', 'change', 'type'])

debug = False

def debugout(str):
    if debug:
        print(str)

#取得HTML数据
def GetHTMLText(url):
    try:
        debugout("Starting get url" + url)
        r = requests.get(url)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return ""

#取得股票列表——东方财富
def GetStockList():
    html = GetHTMLText(StockListUrl)
    s = html.lower()
    page = etree.HTML(s)
    if page==None:
        return
    href = page.xpath('//a')
    for i in href:
        try:
            s = i.text
            #d = re.findall('"(.*")"(""[630][0]\d[4]")"',s)
            d = re.findall(r"[630][0]\d{4}",s)
            if len(d)>0:
                n = s.find(d[0])
                d1 = s[0:n-1]
                if len(d1)>5:
                    continue
                StockList.append(d[0])
                stockdict.update({d[0]:d1})
        except:
            continue

    '''
    #use beautiful soup
    soup = BeautifulSoup(html, 'html.parser')
    a = soup.find_all('a')
    for i in a:
        try:
            href = i.attrs['href']
            s = href
            StockList.append(re.findall(r"[s][hz][630][0]\d{4}", s)[0])
        except:
            continue
    return StockList
    '''
    return StockList


#取得股票当日价格——百度
def getStockInfo(lst, stockURL, fpath):
    count = 0
    errCount = 0
    for stock in lst:
        #重组URL
        if stock[0]=='6':
            s = 'sh'+stock
        elif stock[0]== 's':
            s = stock
        else:
            s = 'sz' + stock
        url = stockURL + s + ".html"
        html = GetHTMLText(url)
        try:
            if html == "":
                continue
            infoDict = {}
            s=html.lower()

            page = etree.HTML(s)
            if page==None:
                return
            stockInfo = page.xpath('//a[@class="bets-name"]')

              name =  (stockInfo[0].text)
            name = name.split()[0]

            infoDict.update({'股票名称': name})

            keylist = page.xpath('//div[@class="bets-content"]/div/dl/dt')
            valueList = page.xpath('//div[@class="bets-content"]/div/dl/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%%   %s  Count: %d Error: %d  Name:%s" % (count * 100 / len(lst), stock, count, errCount,name),
                      end="")
        except:
            count = count + 1
            errCount = errCount + 1
            print("\r当前进度: %.2f%%   %s  Count: %d Error: %d  Name:%s" % (
            count * 100 / len(lst), stock, count, errCount, name),
                  end="")
            continue

#取得十大股东信息——新浪
def GetGDInfo(code,stockurl):
    s =gpCode(code,False,False)
    url = stockurl
    url = url.replace('#code',s)
    html = GetHTMLText(url)
    s = html.lower()
    page = etree.HTML(s)
    if page == None:
        return
    #读取股票名称
    k=page.xpath('//th[@colspan="6"]')
    aName = k[0].text.strip()
    i = aName.find('(')
    aName = aName[0:i]
    aData = ['date', 'code', 'name', 'no.',"price", 'cop', 'total', 'change', 'type']
    aDate = ""
    flag = 0
    aPrice=""

    #其它股东信息
    k = page.xpath('//td/div[@align="center"]')
    for x in k:
        xx = x.xpath("./a")
        if len(xx) > 0 and "name" in xx[0].attrib:
            aDate = (xx[0].attrib['name'])
            ii = aDate[5:7]
            if ii=="03":
                ii="1"
            elif ii=="06":
                ii="2"
            elif ii=="09":
                ii="3"
            else:
                ii="4"
            aPrice=GetJimoPrice(code,aDate[0:4],ii)
            flag = 1
            continue
        s = x.text
        if s==None:
            continue
        s = s.strip()

        #排名
        if re.match("^([1-9]|10)$",s):
            #排名
            aData[0] = aDate
            aData[1] = code
            aData[2] = aName
            aData[3] = s
            aData[4] = aPrice
            for xxx in range(5,9):
                aData[xxx] = "NA"
            flag = 5
        elif flag<<span style="color:#ff0000;">9:
            aData[flag]=s
            flag+=1
        if flag>8:
            with open(GDDataFile, 'a', encoding='utf-8') as f:
                f.write(str(aData)+"\n")
            df.loc[len(df)] = aData
            debugout(aData)

#取得股票季末价格
def GetJimoPrice(code,ayear,ajd):
    url = StockPriceUrl
    url = url.replace("#year",ayear)
    url = url.replace("#jd",ajd)
    url = url.replace("#code",code)
    HTML = GetHTMLText(url)
    s = HTML.lower()
    page = etree.HTML(s)
    if page == None:
        return ""
    x = page.xpath('//tr/td/div[@align="center"]')
    if len(x)>10:
        return x[10].text
    else:
        return ""


#处理股票代码
def gpCode(code,with_s=False,upper=False):
    code = code.lower()
    if with_s:
        if code[0] != "s":
            if code[0]=="6":
                code = "sh"+code
            else:
                code= "sz"+code
    else:
        if code[0]=="s":
            code = code[2:]
    if upper:
        code = code.upper()
    if len(code)==6 or len(code)==8:
        return code
    else:
        return ""



def main():
    debugout("Starting get stock list...")
    GetStockList()
    with open(StockListDataFile, 'w', encoding='utf-8') as f:
        f.write(str(StockList))
    with open(StockDictDataFile, 'w', encoding='utf-8') as f1:
        f1.write(str(stockdict))
    debugout("Starting get stock info......")
    icount=len(StockList)
    idx = 1
    with open(GDDataFile, 'w', encoding='utf-8') as f:
        f.write(str(""))
    for i in StockList:
        GetGDInfo(i,StockGDUrl)
        print ("Processing %s %d of %d"%(i,idx,icount))
        idx+=1
        time.sleep(1)#这个自己看，怎么折腾，不要被封，效率很低，如果自己有代理啥的，自己折腾个线程
        #break #时间太长,且有可能被ban 可以考虑等一秒继续
    df.to_csv(GDDataFile+".csv")
main()