def ctx(category=''):
tree = fetch(f'{domain}/python/topics/{category}')
posts = tree.css('ul.note-list li')
return {
'title': 'CTOLib码库',
'link': domain,
'description': 'Python开发社区',
'author': 'alphardex',
'items': list(map(parse, posts))
}
def ctx(category=''):
tree = fetch(f"{domain}/main/zcgl/zxgg/index.shtml?catalogId=1,5,228")
posts = tree.css('.news_list li')
return {
'title': '东兴资管产品最新公告',
'link': f'{domain}/main/zcgl/zxgg/index.shtml?catalogId=1,5,228',
'description': '东兴资管产品最新公告',
'author': 'hillerliao',
'items': list(map(parse, posts))
}
def ctx(category=''):
tree = fetch(f"{domain}/{category}")
posts = tree.css('.feed_body .pagedlist_item')
return {
'title': '传送门',
'link': domain,
'description': '传送门：微信公众号订阅',
'author': 'alphardex',
'items': list(map(parse, posts))
}
def ctx(category=''):
tree = fetch(f"{domain}/search/scroll/{category}.jsp")
posts = tree.css('dl')
channel_title = tree.css('b').css('b::text').extract_first()
return {
'title': channel_title,
'link': f'{domain}/search/scroll/{category}.jsp',
'description': '财新网滚动新闻',
'author': 'hillerliao',
'items': list(map(parse, posts))
}
def ctx(category=''):
DEFAULT_HEADERS.update(
{'Referer': f'https://www.chaindd.com/column/{category}'})
tree = fetch(f"{domain}/column/{category}")
posts = tree.css('li .cont')
return {
'title': f'链得得栏目{category}最新文章',
'link': f'{domain}/column/{category}',
'description': f'链得得栏目{category}最新文章',
'author': 'hillerliao',
'items': list(map(parse, posts))
}
def ctx(category=''):
tree = fetch(f"{domain}/RssFeed/subjectcode/13-Earnings%20Releases%20And%20Operating%20Results/feedTitle/GlobeNewswire%20-%20Earnings%20Releases%20And%20Operating%20Results")
posts = tree.css('item')
items = list(map(parse, posts))
items = filter_content(items)
return {
'title': 'Earnings Date - Globenewswire',
'link': f'{domain}/RssFeed/subjectcode/13-Earnings%20Releases%20And%20Operating%20Results/feedTitle/GlobeNewswire%20-%20Earnings%20Releases%20And%20Operating%20Results',
'description': 'Earnings Date - Globenewswire',
'author': 'hillerliao',
'items': items
}
def ctx(category=''):
tree = fetch(f"https://feed.{domain}/rss/home/?rss=G1QFDERJXkJeGVtYWA==",
headers=DEFAULT_HEADERS)
posts = tree.css('item')
items = list(map(parse, posts))
items = filter_content(items)
return {
'title': 'Earnings Date - Businesswire',
'link':
f'https://www.{domain}/portal/site/home/news/subject/?vnsId=31407',
'description': 'Earnings Date - Businesswire',
'author': 'hillerliao',
'items': items
}
def ctx(author=''):
url = f"{domain}/author/{author}"
tree = fetch(url=url, headers=DEFAULT_HEADERS)
html = tree.css('body')
mp_name = html.css('h1::text').get().split('：')[-1]
mp_description = html.css('.archive-description::text').get()
posts = html.css('.entry-content-wrap')
return {
'title': f'{mp_name} - 公众号',
'link': url,
'description': mp_description,
'author': 'hillerliao',
'items': list(map(parse, posts))
}
def ctx(category=''):
# DEFAULT_HEADERS.update({'upgrade-insecure-requests': 1})
url = f"{domain}/news-releases/financial-services-latest-news/earnings-list/?page=1&pagesize=100"
tree = fetch(url, headers=DEFAULT_HEADERS)
posts = tree.css('.card-list-hr .row')
items = list(map(parse, posts))
items = filter_content(items)
return {
'title': 'Earnings Date - Prnewswire',
'link': f'{domain}/news-releases/financial-services-latest-news/earnings-list/',
'description': 'Earnings Date - Prnewswire',
'author': 'hillerliao',
'items': items
}
def ctx(category=''):
url = f'{domain}/column/{category}'
DEFAULT_HEADERS.update({'Host': 'www.jintiankansha.me'})
tree = fetch(url, headers=DEFAULT_HEADERS)
posts = tree.css('.cell.item')
items = list(map(parse, posts))
column_title = tree.css('title::text').extract_first()
return {
'title': f'{column_title}',
'description': f'{category}',
'link': url,
'author': f'hillerliao',
'items': items
}
def ctx(gh=''):
global url
url = f"{domain}/weixin?type=1&s_from=input&query={gh}&ie=utf8&_sug_=n&_sug_type_=&w=01019900&sut=1554&sst0=1628603087755&lkt=0%2C0%2C0"
tree = fetch(url=url, headers=DEFAULT_HEADERS)
global dd_num
dd_num = len(tree.css('dd'))
posts = [tree.css('dd')[-1]]
mp_name = tree.css('p.tit a::text').get()
mp_description = tree.css('dd::text')[0].get()
return {
'title': f'{mp_name}-公众号',
'link': url,
'description': mp_description,
'author': 'hillerliao',
'items': list(map(parse, posts))
}
def ctx(category=''):
stock = category
def parse(post):
item = {}
item['description'] = item['title'] = stock.upper() + '的评级：' + ', '.join(post.css('td::text').extract())
item['link'] = url
return item
url = f'{domain}/stock/{category}/ratings'
tree = fetch(url, headers=DEFAULT_HEADERS)
posts = tree.css('tbody tr')
items = list(map(parse, posts))
column_title = tree.css('title::text').extract_first()
return {
'title': f'{column_title} - benzinga',
'description': f'{column_title} - benzinga',
'link': url,
'author': f'hillerliao',
'items': items
}
def get_content(url):
tree = fetch(url=url, headers=DEFAULT_HEADERS)
content = tree.css('.single-content').get()
return content