def get_news(page_count, cb):
page_count *= 10
error_count = 0
time_utc = int(time.time())
for i in range(1, page_count + 1):
response = url_open(
"https://www.chainnews.com/api/articles/feeds/?page=%d&ts=%d" %
(i, time_utc))
#print(response)
json_data = json.loads(response)
for item in json_data['results']:
article_item = news_base.article_info(
item['author_name'], #
item["pb_timestamp"], #
item['title'], #
item['digest'],
item['content'],
item['refer_link'],
"链闻chainnews")
if not cb(article_item):
error_count += 1
else:
error_count = 0
if error_count >= 5:
break
if error_count >= 5:
break
#def get_news(10)
#print(response)
def get_news(page_count, cb):
time_utc = int(time.time())
error_count = 0
for i in range(1, page_count + 1):
response = url_open(
"https://www.55coin.com/index/article/search.html?cat_id=4&page=%d&is_index=1"
% (i))
#print(response)
json_data = json.loads(response)
for item in json_data['list']:
article_item = news_base.article_info(
item['nickname'], int(item["add_time"]), item['title'],
item['brief'], 'content',
'https://www.55coin.com/article/%d.html' % item['article_id'],
"区势传媒")
source_responce = url_open(article_item.source_addr)
source_doc = pq(source_responce)
article_item.content = source_doc(".article-content").html()
if not cb(article_item):
error_count += 1
else:
error_count = 0
if error_count >= 5:
break
if error_count >= 5:
break
#print(json_data['results'][0])
#def get_news(10)
#print(response)
def get_news(page_count, cb):
error_count = 0
time_utc = int(time.time()) * 1000
for i in range(1, page_count + 1):
#print(">>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>")
response = url_open(
"https://www.chainfor.com/home/list/news/data.do?categoryId=&lastItemTimeStamp=%d&device_type=0"
% (time_utc))
#print(response)
json_data = json.loads(response)
for item in json_data['list']:
article_item = news_base.article_info(
item['nickName'], #
int(item["releaseDate"]['time']) / 1000, #
item['title'], #
item["introduction"], #
'content',
"https://www.chainfor.com/news/show/%d.html" % item["id"],
"链向财经")
source_responce = url_open(article_item.source_addr)
source_doc = pq(source_responce)
article_item.content = source_doc(".m-i-bd").html()
time_utc = item["releaseDate"]['time']
if not cb(article_item):
error_count += 1
else:
error_count = 0
if error_count >= 5:
break
if error_count >= 5:
break
#print(article_item)
#print(json_data['results'][0])
#get_news(2)
#def get_news(10)
#print(response)
def get_news(page_count,cb):
error_count = 0
for i in range(1,page_count+1):
response = url_open("https://webapi.8btc.com/bbt_api/news/list?num=20&page=%d"%(i))
#print(response)
json_data = json.loads(response)
for item in json_data['data']['list']:
article_item = news_base.article_info(item['author_info']['display_name'], int(item["post_date"]), item['title'], item['desc'],'content', 'https://www.8btc.com/article/'+str(item['id']), "8比特")
source_responce = url_open(article_item.source_addr)
source_doc = pq(source_responce)
article_item.content = source_doc(".bbt-html").html()
if not cb(article_item):
error_count+=1
else:
error_count = 0
if error_count >= 5:
break
if error_count >= 5:
break
#def get_news(10)
#print(response)
def get_news(page_count, cb):
time_utc = int(time.time())
error_count = 0
index = 0
for i in range(1,page_count+1):
#print(">>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>")
response = url_open("https://api.jinse.com/v6/information/list?catelogue_key=www&limit=23&information_id=%d&flag=down&version=9.9.9&_source=www"%(index))
#print(response)
json_data = json.loads(response)
for item in json_data['list']:
if item["type"] != 1 and item["type"] != 2:
continue
article_item = news_base.article_info(
item["extra"]['author'],#
int(item["extra"]["published_at"]),#
item['title'], #
item["extra"]['summary'],#
'content',
item["extra"]['topic_url'],
"金色财金")
source_responce = url_open(article_item.source_addr)
source_doc = pq(source_responce)
article_item.content = source_doc(".js-article-detail").html() if source_doc(".js-article-detail").html() else source_doc(".js-article").html()
index = item['id']
if not cb(article_item):
error_count+=1
else:
error_count = 0
if error_count >= 5:
break
if error_count >= 5:
break
#print(json_data['results'][0])
#def get_news(10)
#print(response)