1
2
3
4
5
6
7

import re
match = re.search(r'[1-9]\d{5}', 'BIT 100081')
if match:
    print(match.group(0))

    
100081

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19

import re
match = re.match(r'[1-9]\d{5}', 'BIT 100081')
if match:
    match.group(0)

    

match.group(0)
Traceback (most recent call last):
  File "<pyshell#27>", line 1, in <module>
    match.group(0)
AttributeError: 'NoneType' object has no attribute 'group'

match = re.match(r'[1-9]\d{5}', '100081 BIT')
if match:
    match.group(0)

    
'100081'

1
2
3
4

import re
ls = re.findall(r'[1-9]\d{5}', 'BIT100081 TSU100084')
ls
['100081', '100084']

1
2
3
4

re.split(r'[1-9]\d{5}', 'BIT100081 TSU100084')
['BIT', ' TSU', '']
re.split(r'[1-9]\d{5}', 'BIT100081 TSU100084', maxsplit=1)
['BIT', ' TSU100084']

1
2
3
4
5
6
7

for m in re.finditer(r'[1-9]\d{5}', 'BIT100081 TSU100084'):
    if m:
        print(m.group(0))

        
100081
100084

1
2
3

re.sub(r'[1-9]\d{5}', ':zipcode', 'BIT100081 TSU100084')
                       
'BIT:zipcode TSU:zipcode'

1

rst = re.search(r'[1-9]\d{5}', 'BIT 100081')

1
2

pat = re.compile(r'[1-9]\d{5}')
rst = pat.search('BIT 100081')

1

regex = re.compile(r'[1‐9]\d{5}')

 1
 2
 3
 4
 5
 6
 7
 8
 9
10

match = re.search(r'[1-9]\d{5}', 'BIT 100081')
                       
if match:
       print(match.group(0))

                       
100081
type(match)
                       
<class 're.Match'>

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18

import re
m = re.search(r'[1-9]\d{5}', 'BIT100081 TSU100084')
m.string
'BIT100081 TSU100084'
m.re
re.compile('[1-9]\\d{5}')
m.pos
0
m.endpos
19
m.group(0)
'100081'
m.start()
3
m.end()
9
m.span()
(3, 9)

1
2
3

match = re.search(r'PY.*N', 'PYANBNCNDN')
match.group(0)
'PYANBNCNDN'

 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

#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()

 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

#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()

 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

import requests

def get_stock_list():
    # 东方财富股票列表接口（返回 JSON 数据）
    url = "https://push2.eastmoney.com/api/qt/clist/get"

    # 接口参数（核心就在这里）
    params = {
        "pn": 1,      # page number：页码（从 1 开始）
        "pz": 20,     # page size：每页返回多少条数据
        "po": 1,      # 排序方式：1 表示倒序
        "np": 1,      # 是否分页（一般固定为 1）
        "ut": "bd1d9ddb04089700cf9c27f6f7426281",  # 用户标识（东方财富接口固定值）
        "fltt": 2,    # 返回数据格式控制（2 表示返回 float）
        "invt": 2,    # 返回字段类型控制
        "fid": "f3",  # 排序字段（f3 通常表示涨跌幅）
        # fs：股票市场范围
        # m:0  深市
        # t:6  创业板
        # t:13 中小板
        # t:80 科创板
        "fs": "m:0+t:6,m:0+t:13,m:0+t:80",
        # fields：指定返回哪些字段
        # f12：股票代码
        # f14：股票名称
        # f2 ：最新价
        "fields": "f12,f14,f2"
    }

    # 发送 GET 请求
    # proxies 设置为 None 是为了避免本地代理干扰
    r = requests.get(
        url,
        params=params,
        timeout=10,
        proxies={"http": None, "https": None}
    )

    # 如果 HTTP 状态码不是 200，直接抛异常
    r.raise_for_status()

    # 将返回的 JSON 文本解析为 Python 字典
    data = r.json()

    # 返回股票列表（diff 是一个列表，每个元素是一只股票）
    return data["data"]["diff"]


def main():
    # 获取股票数据列表
    stocks = get_stock_list()

    # 打印表头
    print("代码      名称        最新价")
    print("-" * 30)

    # 遍历股票列表并打印
    for s in stocks:
        # s 是一个字典，如：
        # {'f12': '300750', 'f14': '宁德时代', 'f2': 210.35}
        print(f"{s['f12']:8} {s['f14']:8} {s['f2']}")


# Python 程序入口
if __name__ == "__main__":
    main()