python3获取股东的减持信息（转）

男娘i 2023-03-14 08:27 5阅读 0赞

# -*- coding: GB2312 -*-
    import requests
    from bs4 import BeautifulSoup
    import csv
    import time
    import codecs
    
    
    # 获取数据
    def getHTML(url):
        response = requests.get(url)
        print(response.apparent_encoding)  # 返回页面编码：GB2312
    
    
        # 单用GB2312也可以好像
        try:
            print(response.text.encode('GB2312').decode('GB2312'))
        except:
            print(response.text.encode('utf-8').decode('utf-8'))
        return response.text
    
    
    # 处理数据
    def writeFile(writer, res):
        # 返回的数据：var TbrNdpvg={pages:401,data:[]},"url":""}
        startid = res.find("[")
        endid = res.find("]")
        print(startid)
        print(endid)
        new_content = res[startid + 1:endid - 1]
        # print(content_txt[startid:endid])
        list = new_content.split("\",")
        print(len(list))
        new_list = []
        for i in list:
            i = i.replace('"', '')
            new_list.append(i)
        print(new_list)
    
        m = len(new_list)
        for i in range(m):
            # print(type(new_list[i]))
            try:
                new_list[i].encode('GB2312').decode('GB2312')
    
            except:
                new_list[i].encode('utf-8').decode('utf-8')
    
            new_list_i = new_list[i].split(',')
            new_list_i[0] = new_list_i[0] + '\t'  # 写csv，不允许科学计算
    
            print(type(new_list_i))
            print(new_list_i)
            writer.writerow(new_list_i)
    
    
    for i in range(40):
        url = "http://data.eastmoney.com/DataCenter_V3/gdzjc.ashx?pagesize=500&page=" + str(
            i) + "&js=var%20UWExJjvK¶m=&sortRule=-1&sortType=BDJZ&tabid=jjc&code=&name=&rt=50815994"
        print(url)
        res = getHTML(url)
        time.sleep(1)  # 每隔一秒访问
        csvFile = codecs.open('d:/Aa.csv', 'a', encoding='utf8')  # codecs.open() 防止写入乱码
        writer = csv.writer(csvFile)
        writeFile(writer, res)