def __init__(self, html=None, title=" ", **kwargs):
self.html = html or None
self.title = title or None
self.entities = []
self.keywords = []
self.names = []
self.fulltext = None
self.language = None
self.description = None
self.canonical_url = None
self.image = None
self.published_date = None
self.modified_date = None
self.scraped_date = None
self.contenthash = None
self.reading_time = None
config = Configuration()
config.enable_image_fetching = False
self.goose = Goose(config=config)
self.tree = None
res = requests.get(url=url, headers=header)
from lxml import etree
html = etree.HTML(res.text)
a_list = html.xpath('//*[@id="J_posts_list"]/tr/td[2]/p[1]/a[3]/@href')
# print(len(a_list))
uri = 'https://www.cifnews.com/article/30666'
g = Goose({'stopwords_class': StopWordsChinese})
article = g.extract(url=uri)
config = Configuration()
config.enable_image_fetching = True
text = article.cleaned_text
# print(text)
header = {
'User-Agent':
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'
}
# res = requests.get('https://waimaoquan.alibaba.com/bbs/attachment/1809/thread/309_713107_6a75458c47ea357.png', headers=header)
# with open('sds.jpg', 'wb') as j:
# j.write(res.content)
# 要访问的目标页面
targetUrl = "http://test.abuyun.com"
# 代理服务器