newsletter3k,在第一个 "by" 字后的可见文本中查找作者姓名
newsletter3k, find author name in visible text after first "by" word
Newsletter3K 是一个很好的 python 新闻内容提取库。它 大部分 很好用
.我想在可见文本中的第一个“by”字之后提取名称。这是我的代码,效果不佳,请有人帮忙:
import re
from newspaper import Config
from newspaper import Article
from newspaper import ArticleException
from bs4 import BeautifulSoup
from bs4.element import Comment
import urllib.request
USER_AGENT = 'Mozilla/5.0 (Macintosh;Intel Mac OS X 10.15; rv:78.0)Gecko/20100101 Firefox/78.0'
config = Config()
config.browser_user_agent = USER_AGENT
config.request_timeout = 10
html1='https://saugeentimes.com/new-perspectives-a-senior-moment-food-glorious-food-part-2/'
article = Article(html1.strip(), config=config)
article.download()
article.parse()
soup = BeautifulSoup(article)
## I want to take only visible text
[s.extract() for s in soup(['style', 'script', '[document]', 'head', 'title'])]
visible_text = soup.getText()
for line in visible_text:
# Capture one-or-more words after first (By or by) the initial match
match = re.search(r'By (\S+)', line)
# Did we find a match?
if match:
# Yes, process it to print
By = match.group(1)
print('By {}'.format(By))`
这不是一个全面的答案,但它是您可以构建的答案。添加其他源时,您将需要扩展此代码。正如我之前所说,我的 Newspaper3k overview document 有很多提取示例,所以请仔细阅读。
在使用 newspaper3k 尝试这些提取方法后,正则表达式应该是最后的努力:
- article.authors
- 元标签
- json
- 汤
from newspaper import Config
from newspaper import Article
from newspaper.utils import BeautifulSoup
USER_AGENT = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.15; rv:78.0) Gecko/20100101 Firefox/78.0'
config = Config()
config.browser_user_agent = USER_AGENT
config.request_timeout = 10
urls = ['https://saugeentimes.com/new-perspectives-a-senior-moment-food-glorious-food-part-2',
'https://www.macleans.ca/education/what-college-students-in-canada-can-expect-during-covid',
'https://www.cnn.com/2021/02/12/asia/india-glacier-raini-village-chipko-intl-hnk/index.html',
'https://www.latimes.com/california/story/2021-02-13/wildfire-santa-cruz-boulder-creek-residents-fear-water'
'-quality',
'https://foxbaltimore.com/news/local/maryland-lawmakers-move-ahead-with-first-tax-on-internet-ads-02-13-2021']
for url in urls:
try:
article = Article(url, config=config)
article.download()
article.parse()
author = article.authors
if author:
print(author)
elif not author:
soup = BeautifulSoup(article.html, 'html.parser')
author_tag = soup.find(True, {'class': ['td-post-author-name', 'byline']}).find(['a', 'span'])
if author_tag:
print(author_tag.get_text().replace('By', '').strip())
else:
print('no author found')
except AttributeError as e:
pass
Newsletter3K 是一个很好的 python 新闻内容提取库。它 大部分 很好用 .我想在可见文本中的第一个“by”字之后提取名称。这是我的代码,效果不佳,请有人帮忙:
import re
from newspaper import Config
from newspaper import Article
from newspaper import ArticleException
from bs4 import BeautifulSoup
from bs4.element import Comment
import urllib.request
USER_AGENT = 'Mozilla/5.0 (Macintosh;Intel Mac OS X 10.15; rv:78.0)Gecko/20100101 Firefox/78.0'
config = Config()
config.browser_user_agent = USER_AGENT
config.request_timeout = 10
html1='https://saugeentimes.com/new-perspectives-a-senior-moment-food-glorious-food-part-2/'
article = Article(html1.strip(), config=config)
article.download()
article.parse()
soup = BeautifulSoup(article)
## I want to take only visible text
[s.extract() for s in soup(['style', 'script', '[document]', 'head', 'title'])]
visible_text = soup.getText()
for line in visible_text:
# Capture one-or-more words after first (By or by) the initial match
match = re.search(r'By (\S+)', line)
# Did we find a match?
if match:
# Yes, process it to print
By = match.group(1)
print('By {}'.format(By))`
这不是一个全面的答案,但它是您可以构建的答案。添加其他源时,您将需要扩展此代码。正如我之前所说,我的 Newspaper3k overview document 有很多提取示例,所以请仔细阅读。
在使用 newspaper3k 尝试这些提取方法后,正则表达式应该是最后的努力:
- article.authors
- 元标签
- json
- 汤
from newspaper import Config
from newspaper import Article
from newspaper.utils import BeautifulSoup
USER_AGENT = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.15; rv:78.0) Gecko/20100101 Firefox/78.0'
config = Config()
config.browser_user_agent = USER_AGENT
config.request_timeout = 10
urls = ['https://saugeentimes.com/new-perspectives-a-senior-moment-food-glorious-food-part-2',
'https://www.macleans.ca/education/what-college-students-in-canada-can-expect-during-covid',
'https://www.cnn.com/2021/02/12/asia/india-glacier-raini-village-chipko-intl-hnk/index.html',
'https://www.latimes.com/california/story/2021-02-13/wildfire-santa-cruz-boulder-creek-residents-fear-water'
'-quality',
'https://foxbaltimore.com/news/local/maryland-lawmakers-move-ahead-with-first-tax-on-internet-ads-02-13-2021']
for url in urls:
try:
article = Article(url, config=config)
article.download()
article.parse()
author = article.authors
if author:
print(author)
elif not author:
soup = BeautifulSoup(article.html, 'html.parser')
author_tag = soup.find(True, {'class': ['td-post-author-name', 'byline']}).find(['a', 'span'])
if author_tag:
print(author_tag.get_text().replace('By', '').strip())
else:
print('no author found')
except AttributeError as e:
pass