Вот код:
from apiclient.discovery import build
import argparse
import unidecode
import time
import os
import pandas as pd
from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.action_chains import ActionChains
from selenium.webdriver.common.by import By
from textblob import TextBlob
import re
def sentiment(polarity):
if polarity < 0:
p="Negative"
elif polarity > 0:
p="Positive"
else:
p="Neutral"
return p
def scrape_comments(youtube_video_url,Movie_name):
s=Service(r"C:\\Users\\Olga\\Downloads\\chromedriver_win32\\chromedriver.exe")
chrome_path= r"C:\Users\Olga\Downloads\chromedriver_win32\\chromedriver.exe"
driver = webdriver.Chrome(service=s)
driver.get(youtube_video_url)
driver.maximize_window()
driver.implicitly_wait(50)
driver.execute_script('window.scrollTo(0, 600);')
time.sleep(50)
print ("scrolled")
sort= driver.find_element_by_xpath("""//*[@id="icon_label"]""")
driver.implicitly_wait(15)
sort.click()
sort.time.sleep(10)
topcomments =driver.find_elements_by_xpath("""//*[@id="menu"]/a[1]/paper-item-body/div[1]""")
topcomments.click()
time.sleep(10)
for i in range(0,2):
driver.execute_script("window.scrollTo(0,Math.max(document.documentElement.scrollHeight,document.body.scrollHeight?document.documentElement.clientHeight," +
"document.body.scrollHeight,document.documentElement.clientHeight));");
time.sleep(10)
totalcomments= len(driver.find_elements_by_xpath("""//*[@id="content-text"]"""))
if totalcomments < 20:
index= totalcomments
else:
index= 20
ccount = 0
comments= []
while ccount < index:
try:
comment = driver.find_elements_by_xpath('//*[@id="content-text"]')[ccount].text
ccount=ccount+1
print(comment)
comments.append(comment)
except:
comment = ""
polarity=[]
subjectivity=[]
sentiment_type=[]
for elm in comments:
x=TextBlob(elm)
print(elm)
print("Polarity : "+str(x.sentiment.polarity))
print("Subjectivity :"+str(x.sentiment.subjectivity))
polarity.append(x.sentiment.subjectivity)
subjectivity.append(x.sentiment.subjectivity)
s=sentiment(x.sentiment.polarity)
print("Sentiment Type :"+s)
sentiment_type.append(s)
return driver
dataframe={"comment":comments,"polarity":polarity,"sentiment_type":sentiment_type,"sebjectivity":subjectivity}
df = pd.DataFrame.from_dict(dataframe, orient='index')
dfl=df.transpoze()
dfl.columns = ['comment', 'polarity', 'sentiment_type', 'subjectivity']
dfl.to_txt(r"C:\\Users\\Olga\\Desktop\\comment_sentiment_"+Movie_name+".txt", header=True, encoding='utf-8', index=False)
def youtube_video_url(options):
youtube = build("youtube", "v3", developerKey="AIzaSyDuV1ssRswKsW2uUjOWIyXWVh3sDDovBAw")
search_response = youtube.search().list(q=options.q, part="id,snippet", maxResults=options.max_results).execute()
for search_result in search_response.get("items", []):
if search_result["id"]["kind"] == "youtube#video":
videoId = search_result["id"]["videoId"]
print("videoId: " +str(videoId))
url="https://www.youtube.com/watch?v="+videoId
print(url)
return url
if __name__ == "__main__":
print("Enter the Movie Name : ")
Movie_name=str(input())
parser = argparse.ArgumentParser(description='youtube search')
parser.add_argument("--q", help="Search term", default=Movie_name+"Movie Trailer 2020")
parser.add_argument("--max-results", help="Max results", default=1)
args = parser.parse_args()
youtube_video_url=youtube_video_url(args)
scrape_comments(youtube_video_url,Movie_name)
Ошибки которые он выдает:
Warning (from warnings module):
File "C:\Users\Olga\Desktop\1.py", line 44
sort= driver.find_element_by_xpath("""//*[@id="icon_label"]""")
DeprecationWarning: find_element_by_xpath is deprecated. Please use find_element(by=By.XPATH, value=xpath) instead
Traceback (most recent call last):
File "C:\Users\Olga\Desktop\1.py", line 118, in
scrape_comments(youtube_video_url,Movie_name)
File "C:\Users\Olga\Desktop\1.py", line 44, in scrape_comments
sort= driver.find_element_by_xpath("""//*[@id="icon_label"]""")
File "C:\Users\Olga\AppData\Local\Programs\Python\Python310\lib\site-packages\selenium\webdriver\remote\webdriver.py", line 521, in find_element_by_xpath
return self.find_element(by=By.XPATH, value=xpath)
File "C:\Users\Olga\AppData\Local\Programs\Python\Python310\lib\site-packages\selenium\webdriver\remote\webdriver.py", line 1248, in find_element
return self.execute(Command.FIND_ELEMENT, {
File "C:\Users\Olga\AppData\Local\Programs\Python\Python310\lib\site-packages\selenium\webdriver\remote\webdriver.py", line 425, in execute
self.error_handler.check_response(response)
File "C:\Users\Olga\AppData\Local\Programs\Python\Python310\lib\site-packages\selenium\webdriver\remote\errorhandler.py", line 247, in check_response
raise exception_class(message, screen, stacktrace)
selenium.common.exceptions.NoSuchElementException: Message: no such element: Unable to locate element: {"method":"xpath","selector":"//*[@id="icon_label"]"}
(Session info: chrome=100.0.4896.60)
Stacktrace:
Backtrace:
Ordinal0 [0x00449943+2595139]
Ordinal0 [0x003DC9F1+2148849]
Ordinal0 [0x002D4528+1066280]
Ordinal0 [0x00300FD4+1249236]
Ordinal0 [0x003011CB+1249739]
Ordinal0 [0x0032D812+1431570]
Ordinal0 [0x0031BA34+1358388]
Ordinal0 [0x0032BAF2+1424114]
Ordinal0 [0x0031B806+1357830]
Ordinal0 [0x002F6086+1204358]
Ordinal0 [0x002F6F96+1208214]
GetHandleVerifier [0x005EB232+1658114]
GetHandleVerifier [0x006A312C+2411516]
GetHandleVerifier [0x004DF261+560433]
GetHandleVerifier [0x004DE366+556598]
Ordinal0 [0x003E286B+2173035]
Ordinal0 [0x003E75F8+2192888] 
