Question

我正在尝试逐步将csv文件的第一列中的值加载到URL中，并一次请求一个URL，延迟时间为5秒。第一列中的每个值都应替换“theid”

到目前为止，这是我的代码：

 # I have a defined function
 def withid (theid):
    """"""


    global cache

    dupe = False

    theurl = "{0}{1}{2}".format(OMDBURL, "?i=", theid)

    response = urllib2.urlopen(theurl)

    movdata = json.load(response)

    for mov in cache:
        if movdata[MKEY[1]] == mov[MKEY[1]]:
            dupe = True
    if not dupe:
        cache.append(movdata)



outfile2 = open('outputrows2-shortened.csv', 'rb')
for row in outfile2:
  theid = outfile2(row[0])
  time.sleep(5)

输出：TypeError：'file'对象不可调用

Answer 1

您的withid()函数永远不会返回任何内容。尝试在其末尾添加return movdata。

这是一个可能有用的重写版本：

import csv
import json
import time
import urllib2

PAGE_DELAY = 5.    # time between loading pages
PAGE_LOAD  = 0.3   # how long it takes to load a page

make_url = 'http://www.imdb.com/title/tt{}/'.format

def get_csv_column(csv_fname, col, **kwargs):
    with open(csv_fname, 'rb') as inf:
        incsv = csv.reader(inf, **kwargs)
        column = [row[col] for row in incsv]
    return column

def get_data_by_id(id):
    url = make_url(id)
    response = urllib2.urlopen(url)
    data = json.load(response)
    return id,data

def delayed(delay, fn, *args):
    time.sleep(delay)
    return fn(*args)

def human_time(seconds):
    if seconds >= 86400:
        return '{:0.1f} days'.format(seconds / 86400.)
    elif seconds >= 3600:
        return '{:0.1f} hours'.format(seconds / 3600.)
    elif seconds >= 60:
        return '{:0.1f} minutes'.format(minutes / 60.)
    else:
        return '{:0.1f} seconds'.format(seconds)

def main():
    ids = get_csv_column('outputrows2.csv', 0)

    expected = (PAGE_DELAY + PAGE_LOAD) * len(ids)
    print('This will take about {}.'.format(human_time(expected)))

    results = (delayed(PAGE_DELAY, get_data_by_id, id) for id in ids)
    moviedata = dict(results)     # => gives dict of {id:data}

if __name__=="__main__":
    main()

尝试延迟运行已定义的函数

1 个答案: