谷歌金融错误：无效的li

Question

我正试图为学校做个人项目（股票市场预测），这时谷歌又开始行动了。。。在

我意识到谷歌金融在过去的一年里完全是垃圾，但直到今天早上它似乎仍在运行。 我第一次运行代码时遇到了一个错误，尽管它昨天运行得很好。在

所以我试着从实际的库页面运行一个示例代码：https://pypi.org/project/googlefinance.client/

!pip install googlefinance.client

from googlefinance.client import get_price_data, get_prices_data, get_prices_time_data

# Dow Jones
param = {
    'q': ".DJI", # Stock symbol (ex: "AAPL")
    'i': "86400", # Interval size in seconds ("86400" = 1 day intervals)
    'x': "INDEXDJX", # Stock exchange symbol on which stock is traded (ex: "NASD")
    'p': "1Y" # Period (Ex: "1Y" = 1 year)
}
# get price data (return pandas dataframe)
df = get_price_data(param)
print(df)

params = [
    # Dow Jones
    {
        'q': ".DJI",
        'x': "INDEXDJX",
    },
    # NYSE COMPOSITE (DJ)
    {
        'q': "NYA",
        'x': "INDEXNYSEGIS",
    },
    # S&P 500
    {
        'q': ".INX",
        'x': "INDEXSP",
    }
]
period = "1Y"
# get open, high, low, close, volume data (return pandas dataframe)
df = get_prices_data(params, period)
print(df)

但仍然有

^{pr2}$

以前有没有人遇到过这种情况，知道出了什么问题或如何解决它？在

或者，在另一个问题上，有人知道谷歌金融的一个好的替代品吗？在

Answer 1

这是示例代码的问题。如果您转到GitHub Homepage，您将获得最新版本，甚至是一些小的更新。在

我稍微修改了client.py，输出没有问题。在

#!/usr/bin/env python
# coding: utf-8
import requests
from datetime import datetime
import pandas as pd


def get_price_data(query):
    r = requests.get(
        "https://finance.google.com/finance/getprices", params=query)
    lines = r.text.splitlines()
    data = []
    index = []
    basetime = 0
    for price in lines:
        cols = price.split(",")
        if cols[0][0] == 'a':
            basetime = int(cols[0][1:])
            index.append(datetime.fromtimestamp(basetime))
            data.append([float(cols[4]), float(cols[2]), float(
                cols[3]), float(cols[1]), int(cols[5])])
        elif cols[0][0].isdigit():
            date = basetime + (int(cols[0]) * int(query['i']))
            index.append(datetime.fromtimestamp(date))
            data.append([float(cols[4]), float(cols[2]), float(
                cols[3]), float(cols[1]), int(cols[5])])
    return pd.DataFrame(data, index=index, columns=['Open', 'High', 'Low', 'Close', 'Volume'])


def get_closing_data(queries, period):
    closing_data = []
    for query in queries:
        query['i'] = 86400
        query['p'] = period
        r = requests.get(
            "https://finance.google.com/finance/getprices", params=query)
        lines = r.text.splitlines()
        data = []
        index = []
        basetime = 0
        for price in lines:
            cols = price.split(",")
            if cols[0][0] == 'a':
                basetime = int(cols[0][1:])
                date = basetime
                data.append(float(cols[1]))
                index.append(datetime.fromtimestamp(date).date())
            elif cols[0][0].isdigit():
                date = basetime + (int(cols[0]) * int(query['i']))
                data.append(float(cols[1]))
                index.append(datetime.fromtimestamp(date).date())
        s = pd.Series(data, index=index, name=query['q'])
        closing_data.append(s[~s.index.duplicated(keep='last')])
    return pd.concat(closing_data, axis=1)


def get_open_close_data(queries, period):
    open_close_data = pd.DataFrame()
    for query in queries:
        query['i'] = 86400
        query['p'] = period
        r = requests.get(
            "https://finance.google.com/finance/getprices", params=query)
        lines = r.text.splitlines()
        data = []
        index = []
        basetime = 0
        for price in lines:
            cols = price.split(",")
            if cols[0][0] == 'a':
                basetime = int(cols[0][1:])
                date = basetime
                data.append([float(cols[4]), float(cols[1])])
                index.append(datetime.fromtimestamp(date).date())
            elif cols[0][0].isdigit():
                date = basetime + (int(cols[0]) * int(query['i']))
                data.append([float(cols[4]), float(cols[1])])
                index.append(datetime.fromtimestamp(date).date())
        df = pd.DataFrame(data, index=index, columns=[
                          query['q'] + '_Open', query['q'] + '_Close'])
        open_close_data = pd.concat(
            [open_close_data, df[~df.index.duplicated(keep='last')]], axis=1)
    return open_close_data


def get_prices_data(queries, period):
    prices_data = pd.DataFrame()
    for query in queries:
        query['i'] = 86400
        query['p'] = period
        r = requests.get(
            "https://finance.google.com/finance/getprices", params=query)
        lines = r.text.splitlines()
        data = []
        index = []
        basetime = 0
        for price in lines:
            cols = price.split(",")
            if cols[0][0] == 'a':
                basetime = int(cols[0][1:])
                date = basetime
                data.append([float(cols[4]), float(cols[2]), float(
                    cols[3]), float(cols[1]), int(cols[5])])
                index.append(datetime.fromtimestamp(date).date())
            elif cols[0][0].isdigit():
                date = basetime + (int(cols[0]) * int(query['i']))
                data.append([float(cols[4]), float(cols[2]), float(
                    cols[3]), float(cols[1]), int(cols[5])])
                index.append(datetime.fromtimestamp(date).date())
        df = pd.DataFrame(data, index=index, columns=[
                          query['q'] + '_Open', query['q'] + '_High', query['q'] + '_Low', query['q'] + '_Close', query['q'] + '_Volume'])
        prices_data = pd.concat(
            [prices_data, df[~df.index.duplicated(keep='last')]], axis=1)
    return prices_data


def get_prices_time_data(queries, period, interval):
    prices_time_data = pd.DataFrame()
    for query in queries:
        query['i'] = interval
        query['p'] = period
        r = requests.get(
            "https://finance.google.com/finance/getprices", params=query)
        lines = r.text.splitlines()
        data = []
        index = []
        basetime = 0
        for price in lines:
            cols = price.split(",")
            if cols[0][0] == 'a':
                basetime = int(cols[0][1:])
                date = basetime
                data.append([float(cols[4]), float(cols[2]), float(
                    cols[3]), float(cols[1]), int(cols[5])])
                index.append(datetime.fromtimestamp(date))
            elif cols[0][0].isdigit():
                date = basetime + (int(cols[0]) * int(query['i']))
                data.append([float(cols[4]), float(cols[2]), float(
                    cols[3]), float(cols[1]), int(cols[5])])
                index.append(datetime.fromtimestamp(date))
        df = pd.DataFrame(data, index=index, columns=[
                          query['q'] + '_Open', query['q'] + '_High', query['q'] + '_Low', query['q'] + '_Close', query['q'] + '_Volume'])
        prices_time_data = pd.concat(
            [prices_time_data, df[~df.index.duplicated(keep='last')]], axis=1)
    return prices_time_data

片段

^{pr2}$

输出

Volume Open High ... Close
328405532 2017-08-01 15:00:00 21961.42 21990.96 ... 21963.92
328405532 2017-08-02 15:00:00 22004.36 22036.10 ... 22016.24
336824836 2017-08-03 15:00:00 22007.58 22044.85 ... 22026.10
278731064 2017-08-04 15:00:00 22058.39 22092.81 ... 22092.81
253635270 2017-08-07 15:00:00 22100.20 22121.15 ... 22118.42
213012378 2017-08-08 15:00:00 22095.14 22179.11 ... 22085.34

Answer 2

在过去的48小时左右，".INX"没有在我的google页面上更新。.DJI和{}仍在更新，尽管我认为其中一个最近没有更新。在