Python 利用熊猫从温德古德获取天气数据

我在Shane Lynn上找到了一套非常有用的脚本 . 第一个脚本用于从Weather Underground中提取数据，如下所示：

import requests
import pandas as pd
from dateutil import parser, rrule
from datetime import datetime, time, date
import time

def getRainfallData(station, day, month, year):
    """
    Function to return a data frame of minute-level weather data for a single Wunderground PWS station.

    Args:
        station (string): Station code from the Wunderground website
        day (int): Day of month for which data is requested
        month (int): Month for which data is requested
        year (int): Year for which data is requested

    Returns:
        Pandas Dataframe with weather data for specified station and date.
    """
    url = "http://www.wunderground.com/weatherstation/WXDailyHistory.asp?ID={station}&day={day}&month={month}&year={year}&graphspan=day&format=1"
    full_url = url.format(station=station, day=day, month=month, year=year)
    # Request data from wunderground data
    response = requests.get(full_url, headers={'User-agent': 'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2228.0 Safari/537.36'})
    data = response.text
    # remove the excess <br> from the text data
    data = data.replace('<br>', '')
    # Convert to pandas dataframe (fails if issues with weather station)
    try:
        dataframe = pd.read_csv(io.StringIO(data), index_col=False)
        dataframe['station'] = station
    except Exception as e:
        print("Issue with date: {}-{}-{} for station {}".format(day,month,year, station))
        return None
    return dataframe

# Generate a list of all of the dates we want data for
start_date = "2016-08-01"
end_date = "2016-08-31"
start = parser.parse(start_date)
end = parser.parse(end_date)
dates = list(rrule.rrule(rrule.DAILY, dtstart=start, until=end))

# Create a list of stations here to download data for
stations = ["ILONDON28"]
# Set a backoff time in seconds if a request fails
backoff_time = 10
data = {}

# Gather data for each station in turn and save to CSV.
for station in stations:
    print("Working on {}".format(station))
    data[station] = []
    for date in dates:
        # Print period status update messages
        if date.day % 10 == 0:
            print("Working on date: {} for station {}".format(date, station))
        done = False
        while done == False:
            try:
                weather_data = getRainfallData(station, date.day, date.month, date.year)
                done = True
            except ConnectionError as e:
                # May get rate limited by Wunderground.com, backoff if so.
                print("Got connection error on {}".format(date))
                print("Will retry in {} seconds".format(backoff_time))
                time.sleep(10)
        # Add each processed date to the overall data
        data[station].append(weather_data)
    # Finally combine all of the individual days and output to CSV for analysis.
    pd.concat(data[station]).to_csv("data/{}_weather.csv".format(station))

有人能帮我解决这个错误吗

---

所选电台和时段的数据可用，如图所示。

您得到的输出是因为引发了异常。如果添加了

print e

，您会发现这是因为脚本顶部缺少

import io

。其次，你给出的电台名称由一个字符表示。请尝试以下操作：

import io
import requests
import pandas as pd
from dateutil import parser, rrule
from datetime import datetime, time, date
import time

def getRainfallData(station, day, month, year):
    """
    Function to return a data frame of minute-level weather data for a single Wunderground PWS station.

    Args:
        station (string): Station code from the Wunderground website
        day (int): Day of month for which data is requested
        month (int): Month for which data is requested
        year (int): Year for which data is requested

    Returns:
        Pandas Dataframe with weather data for specified station and date.
    """

    url = "http://www.wunderground.com/weatherstation/WXDailyHistory.asp?ID={station}&day={day}&month={month}&year={year}&graphspan=day&format=1"
    full_url = url.format(station=station, day=day, month=month, year=year)

    # Request data from wunderground data
    response = requests.get(full_url)
    data = response.text
    # remove the excess <br> from the text data
    data = data.replace('<br>', '')

    # Convert to pandas dataframe (fails if issues with weather station)
    try:
        dataframe = pd.read_csv(io.StringIO(data), index_col=False)
        dataframe['station'] = station
    except Exception as e:
        print("Issue with date: {}-{}-{} for station {}".format(day,month,year, station))
        return None

    return dataframe

# Generate a list of all of the dates we want data for
start_date = "2016-08-01"
end_date = "2016-08-31"
start = parser.parse(start_date)
end = parser.parse(end_date)
dates = list(rrule.rrule(rrule.DAILY, dtstart=start, until=end))

# Create a list of stations here to download data for
stations = ["ILONDONL28"]
# Set a backoff time in seconds if a request fails
backoff_time = 10
data = {}

# Gather data for each station in turn and save to CSV.
for station in stations:
    print("Working on {}".format(station))
    data[station] = []
    for date in dates:
        # Print period status update messages
        if date.day % 10 == 0:
            print("Working on date: {} for station {}".format(date, station))
        done = False
        while done == False:
            try:
                weather_data = getRainfallData(station, date.day, date.month, date.year)
                done = True
            except ConnectionError as e:
                # May get rate limited by Wunderground.com, backoff if so.
                print("Got connection error on {}".format(date))
                print("Will retry in {} seconds".format(backoff_time))
                time.sleep(10)
        # Add each processed date to the overall data
        data[station].append(weather_data)
    # Finally combine all of the individual days and output to CSV for analysis.
    pd.concat(data[station]).to_csv(r"data/{}_weather.csv".format(station))

---

如果您没有获得CSV文件，我建议您为输出文件名添加完整路径。

Martin，非常感谢。站名在我的脚本中是正确的（但在我复制的代码中是错误的）。添加

import io

实际上解决了这一问题。wonderground的html地址是否可能已更改？我得到了一个类似“错误404：找不到页面”的错误，如果您正确复制/粘贴了脚本，则不应出现

找不到页面
错误，但网站似乎已更改，因此不再返回数据。它可能需要不同的URL格式。
import io
import requests
import pandas as pd
from dateutil import parser, rrule
from datetime import datetime, time, date
import time

def getRainfallData(station, day, month, year):
    """
    Function to return a data frame of minute-level weather data for a single Wunderground PWS station.

    Args:
        station (string): Station code from the Wunderground website
        day (int): Day of month for which data is requested
        month (int): Month for which data is requested
        year (int): Year for which data is requested

    Returns:
        Pandas Dataframe with weather data for specified station and date.
    """

    url = "http://www.wunderground.com/weatherstation/WXDailyHistory.asp?ID={station}&day={day}&month={month}&year={year}&graphspan=day&format=1"
    full_url = url.format(station=station, day=day, month=month, year=year)

    # Request data from wunderground data
    response = requests.get(full_url)
    data = response.text
    # remove the excess <br> from the text data
    data = data.replace('<br>', '')

    # Convert to pandas dataframe (fails if issues with weather station)
    try:
        dataframe = pd.read_csv(io.StringIO(data), index_col=False)
        dataframe['station'] = station
    except Exception as e:
        print("Issue with date: {}-{}-{} for station {}".format(day,month,year, station))
        return None

    return dataframe

# Generate a list of all of the dates we want data for
start_date = "2016-08-01"
end_date = "2016-08-31"
start = parser.parse(start_date)
end = parser.parse(end_date)
dates = list(rrule.rrule(rrule.DAILY, dtstart=start, until=end))

# Create a list of stations here to download data for
stations = ["ILONDONL28"]
# Set a backoff time in seconds if a request fails
backoff_time = 10
data = {}

# Gather data for each station in turn and save to CSV.
for station in stations:
    print("Working on {}".format(station))
    data[station] = []
    for date in dates:
        # Print period status update messages
        if date.day % 10 == 0:
            print("Working on date: {} for station {}".format(date, station))
        done = False
        while done == False:
            try:
                weather_data = getRainfallData(station, date.day, date.month, date.year)
                done = True
            except ConnectionError as e:
                # May get rate limited by Wunderground.com, backoff if so.
                print("Got connection error on {}".format(date))
                print("Will retry in {} seconds".format(backoff_time))
                time.sleep(10)
        # Add each processed date to the overall data
        data[station].append(weather_data)
    # Finally combine all of the individual days and output to CSV for analysis.
    pd.concat(data[station]).to_csv(r"data/{}_weather.csv".format(station))