LXML爬虫——当日开放式基金净值

#查询排行榜,获得基金的名称、代号、单位净值

import requests

from lxml import etree

import xlwt

# 基金名称+基金代码

symbol_url_0 =  'http://stock1.sina.cn/dpool/stock_new/v2/ofdata_center.php?yw_type=jzpaihang&of_type=open&ph=symbol &page={}&vt=4'

# 基金名称+单位净值

per_nav_url_0 = 'http://stock1.sina.cn/dpool/stock_new/v2/ofdata_center.php?yw_type=jzpaihang&of_type=open&ph=per_nav&page={}&vt=4'

symbol_url=symbol_url_0.format('1')

res = requests.get(symbol_url)

res.encoding = 'utf-8'

html = etree.HTML(res.text.encode('utf-8'))

pagecount=int(html.xpath('/html/body/div[1]/div/div[3]/form/div/text()[3]')[0].split('/')[1].split('页')[0])

#print('总共',pagecount,'页')

#print(html)

name_list=[]

symbol_list=[]

per_nav_list=[]

print('*********获得基金名称*********')

#获得基金名称+基金代码

for page in range(1,pagecount + 1):

    print('第'+str(page)+'页 共'+str(pagecount)+'页')

    symbol_url = symbol_url_0.format(str(page))

    res = requests.get(symbol_url)

    res.encoding = 'utf-8'

    html = etree.HTML(res.text.encode('utf-8'))

    for i in range(1,21):

        try:

            name=  html.xpath('/html/body/div[1]/div/div[3]/a[{}]/text()'.format(i+5))[0].strip()

            symbol= html.xpath('/html/body/div[1]/div/div[3]/text()[{}]'.format(i*2+6))[0].strip()

        except:

            continue

        if symbol.isalnum():

            name_list.append(name)

            symbol_list.append(symbol)

            per_nav_list.append(0.000)

            #print(name , symbol)

        else:

            break

print('*********获得基金净值*********')

#获得基金净值

j = 0

for page in range(1,pagecount + 1):

    print('第'+str(page)+'页 共'+str(pagecount)+'页')

    per_nav_url = per_nav_url_0.format(str(page))

    res = requests.get(per_nav_url)

    res.encoding = 'utf-8'

    html = etree.HTML(res.text.encode('utf-8'))

    for i in range(1,21):

        try:

            name = html.xpath('/html/body/div[1]/div/div[3]/a[{}]/text()'.format(i+5))[0].strip()

            per_nav = html.xpath('/html/body/div[1]/div/div[3]/text()[{}]'.format(i*2+5))[0].strip()

        except:

            continue

        if not per_nav.replace('.', '').isdecimal(): #本次查到的金额异常,则放弃

            continue

        try:

            j = name_list.index(name)

        except:

            continue #本次查到的基金名称在列表中不存在,则放弃

        print(name, per_nav, '=>',j,name_list[j])

        per_nav_list[j] = per_nav

print('*********输出全部数据*********')

book = xlwt.Workbook(encoding='utf-8')

sheet = book.add_sheet('当日基金净值表')

for k in range(1,len(name_list) + 1):

    print(symbol_list[k - 1], name_list[k - 1], per_nav_list[k - 1])

    sheet.write(k - 1, 0, symbol_list[k - 1])

    sheet.write(k - 1, 1, name_list[k - 1])

    sheet.write(k - 1, 2, per_nav_list[k - 1])

book.save('D:\当日开放式基金净值表.xls')