目标：我正在尝试根据关键字下载新闻文章以进行情感分析。
这段代码几个月前还在工作，但现在它返回一个空值。我尝试解决此问题，但links=soup.select(".r a")返回空值。
import pandas as pd
import requests
from bs4 import BeautifulSoup
import string
import nltk
from urllib.request import urlopen
import sys
import webbrowser
import newspaper
import time
from newspaper import Article
Company_name1 =[]
Article_number1=[]
Article_Title1=[]
Article_Authors1=[]
Article_pub_date1=[]
Article_Text1=[]
Article_Summary1=[]
Article_Keywords1=[]
Final_dataframe=[]
class Newspapr_pd:
def __init__(self,term):
self.term=term
self.subjectivity=0
self.sentiment=0
self.url='https://www.google.com/search?q={0}&safe=active&tbs=qdr:w,sdb:1&tbm=nws&source=lnt&dpr=1'.format(self.term)
def NewsArticlerun_pd(self):
response=requests.get(self.url)
response.raise_for_status()
#print(response.text)
soup=bs4.BeautifulSoup(response.text,'html.parser')
links=soup.select(".r a")
numOpen = min(5, len(links))
Article_number=0
for i in range(numOpen):
response_links = webbrower.open("https://www.google.com" + links[i].get("href"))
#For different language newspaper refer above table
article = Article(response_links, language="en") # en for English
Article_number+=1
print('*************************************************************************************')
Article_number1.append(Article_number)
Company_name1.append(self.term)
#To download the article
try:
article.download()
#To parse the article
article.parse()
#To perform natural language processing ie..nlp
article.nlp()
#To extract title
Article_Title1.append(article.title)
#To extract text
Article_Text1.append(article.text)
#To extract Author name
Article_Authors1.append(article.authors)
#To extract article published date
Article_pub_date1.append(article.publish_date)
#To extract summary
Article_Summary1.append(article.summary)
#To extract keywords
Article_Keywords1.append(article.keywords)
except:
print('Error in loading page')
continue
for art_num,com_name,title,text,auth,pub_dt,summaries,keywds in zip(Article_number1,Company_name1,Article_Title1,Article_Text1,Article_Authors1,Article_pub_date1,Article_Summary1,Article_Keywords1):
Final_dataframe.append({'Article_link_num':art_num, 'Company_name':com_name,'Article_Title':title,'Article_Text':text,'Article_Author':auth,
'Article_Published_date':pub_dt,'Article_Summary':summaries,'Article_Keywords':keywds})
list_of_companies=['Amazon','Jetairways','nirav modi']
for i in list_of_companies:
comp = str('"'+ i + '"')
a=Newspapr_pd(comp)
a.NewsArticlerun_pd()
Final_new_dataframe=pd.DataFrame(Final_dataframe)
Final_new_dataframe.tail()