Question

我正在遵循此tutorial来从新闻站点检索数据。

主要功能是getDailyNews。它将在每个新闻源上循环，请求api，提取数据并将其转储到pandas DataFrame，然后将结果导出到csv文件中。

但是当我运行代码时，出现了错误。

import requests
from bs4 import BeautifulSoup
import pandas as pd
from datetime import datetime
from tqdm import tqdm, tqdm_notebook
from functools import reduce


def getSources():
    source_url = 'https://newsapi.org/v1/sources?language=en'
    response = requests.get(source_url).json()
    sources = []
    for source in response['sources']:
        sources.append(source['id'])
    return sources

def mapping():
    d = {}
    response = requests.get('https://newsapi.org/v1/sources?language=en')
    response = response.json()
    for s in response['sources']:
        d[s['id']] = s['category']
    return d

def category(source, m):
    try:
        return m[source]
    except:
        return 'NC'

def getDailyNews():
    sources = getSources()
    key = '96f279e1b7f845669089abc016e915cc'


    url = 'https://newsapi.org/v1/articles?source={0}&sortBy={1}&apiKey={2}'
    responses = []
    for i, source in tqdm_notebook(enumerate(sources), total=len(sources)):

        try:
            u = url.format(source, 'top', key)
        except:
            u = url.format(source, 'latest', key)

        response = requests.get(u)
        r = response.json()
        try:
            for article in r['articles']:
                article['source'] = source
            responses.append(r)
        except:
            print('Rate limit exceeded ... please wait and retry in 6 hours')
            return None

    articles = list(map(lambda r: r['articles'], responses))
    articles = list(reduce(lambda x,y: x+y, articles))

    news = pd.DataFrame(articles)
    news = news.dropna()
    news = news.drop_duplicates()
    news.reset_index(inplace=True, drop=True)
    d = mapping()
    news['category'] = news['source'].map(lambda s: category(s, d))
    news['scraping_date'] = datetime.now()

    try:
        aux = pd.read_csv('./data/news.csv')
        aux = aux.append(news)
        aux = aux.drop_duplicates('url')
        aux.reset_index(inplace=True, drop=True)
        aux.to_csv('./data/news.csv', encoding='utf-8', index=False)
    except:
        news.to_csv('./data/news.csv', index=False, encoding='utf-8')

    print('Done')

if __name__=='__main__':
    getDailyNews()

错误：

FileNotFoundError: [Errno 2] No such file or directory: './data/news.csv'

我知道我必须在pd.read_csv中给出路径名，但是我不知道在这里必须给出哪个路径。

Answer 1

如果您要从中执行该程序的目录中没有data文件夹，则此错误将很有意义。帖子here中也存在类似的问题。

无法将熊猫数据框存储为csv

1 个答案: