python/spiderstock.py at master · loulan-D/python · GitHub

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
import requests
from bs4 import BeautifulSoup
import traceback    #不知道功能
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()
"""
#CrawBaiduStocksB.py
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()"""