1
我正在使用以下代碼。除了「隸屬關係」部分,一切都有效。 它返回一個錯誤: AttributeError的:「NoneType」對象有沒有屬性「文本」 沒有的.text,它返回的一切 - 整個代碼的類裏面使用python進行網頁抓取以提取數據
import requests
import bs4
import re
headers = {'User-Agent':'Mozilla/5.0'}
url = 'http://pubs.acs.org/toc/jacsat/139/5'
html = requests.get(url, headers=headers)
soup = bs4.BeautifulSoup(html.text, 'lxml')
tags = soup.findAll('a', href=re.compile("full"))
for tag in tags:
new_url = tag.get('href', None)
newurl = 'http://pubs.acs.org' + new_url
newhtml = requests.get(newurl, headers=headers)
newsoup = bs4.BeautifulSoup(newhtml.text, 'lxml')
article_title = newsoup.find(class_="articleTitle").text
print(article_title)
affiliations = newsoup.find(class_="affiliations").text
print(affiliations)
authors = newsoup.find(id="authors").text
print(authors)
citation_year = newsoup.find(class_="citation_year").text
print(citation_year)
citation_volume = newsoup.find(class_="citation_volume").text
print(citation_volume)
citation = newsoup.find(id="citation").text
print(citation)
pubdate = newsoup.find(id="pubDate").text
print(pubdate)