python 3.6中的youtube视频评论下载程序

时间:2018-06-11 14:27:22

标签: python

“无法写入csv文件”

import simplejson as json
from urllib.request import urlopen
import sys
import time
import csv
import os
import io
os.chdir(r'C:\Users\adity\Desktop\data science')
csvFile =open('test1.csv',"w")
csvFile.write("comments\n")
STAGGER_TIME = 1 

打开网址和屏幕名称(网页名称是要返回结果的用户的网页名称)

url = "https://www.googleapis.com/youtube/v3/commentThreads?key=AIzaSyCYkTUjKgFGcKDnkNQMgSBbb4obnqIzUEM&textFormat=plainText&part=snippet&videoId=Ye8mB6VsUHw&maxResults=20"

这将获取一个python对象并将其转储到一个JSON

字符串
url1=urlopen(url)
#data = json.load(urllib2.urlopen(url))
result = json.load(url1)


# print the result
itemList= result.get("items")
length=len(itemList)

for i in range(0,length):
    results= result["items"][i].get('snippet').get("topLevelComment").get('snippet').get("textDisplay")
    print(results)
    results=results.replace(",", "")
    #print (result["items"][i].get('snippet').get("topLevelComment").get('snippet').get("textDisplay")).encode("utf-8")
    #writer.writerow((result["items"][i].get('snippet').get("topLevelComment").get('snippet').get("textDisplay")).encode("utf-8"))
    csvFile.write(results)
    csvFile.write('\n')
    time.sleep(STAGGER_TIME)

csvFile.close()

“得到错误”

UnicodeEncodeError                        Traceback (most recent call last)
<ipython-input-4-cbf9fd267c8a> in <module>()
     28     print(results)
     29     results=results.replace(",", "")
---> 30     csvFile.write(results)
     31     csvFile.write('\n')
     32     time.sleep(STAGGER_TIME)

~\Anaconda3\lib\encodings\cp1252.py in encode(self, input, final)
     17 class IncrementalEncoder(codecs.IncrementalEncoder):
     18     def encode(self, input, final=False):
---> 19         return codecs.charmap_encode(input,self.errors,encoding_table)[0]
     20 
     21 class IncrementalDecoder(codecs.IncrementalDecoder):

UnicodeEncodeError: 'charmap' codec can't encode characters in position 20-23: character maps to <undefined>

.encode(utf-8)给出了一个typerror

results= result["items"][i].get('snippet').get("topLevelComment").get('snippet').get("textDisplay").encode(utf-8) did help as after using it as it gives 

 34         results=results.replace(",", "")


TypeError: a bytes-like object is required, not 'str'

0 个答案:

没有答案