def get_summary(self, max_num=100):
"""
@attention: 通过内容获取摘要
"""
from common import utils
return utils.get_summary_from_html_by_sub(self.content,
max_num=max_num)
def auto_publish_article(key):
from common.utils import get_summary_from_html_by_sub
# text = open((u"./txt/%s.txt" % u"【原创】《大雄股市历险记4》股票为什么会上涨").encode("utf8"), "r").read()
# text = get_summary_from_html_by_sub(text, max_num=990000)
# print text
# return
count = 0
hrefs = u""
for index in range(20):
url = 'http://weixin.sogou.com/weixin?query=' + key + '&type=2&ie=utf8&page=' + str(
index) + '&p=40040100&dp=1&w=01019900&dr=1'
rep = requests.get(url)
text = rep.text
jq = pq(text)
lst_articles = jq('.wx-rb3 .txt-box a')
for article in lst_articles:
print count
href = article.get("href")
name = article.text_content()
text = requests.get(href).text
text = get_summary_from_html_by_sub(text,
max_num=990000,
filter_nbsp=True)
re_blank = re.compile('[\s]+', re.I)
key_text = re_blank.sub('', text)
if not 300 < len(key_text) < 3000:
continue
if is_in_baidu(key_text[50:60]):
continue
if is_in_baidu(key_text[150:160]):
continue
if is_in_baidu(key_text[250:260]):
continue
count += 1
hrefs += u"%s\n" % href
open((u"./txt/%s.txt" % name).encode("utf8"),
"w").write(text.encode("utf8"))
# break
open((u"./txt/hrefs.txt").encode("utf8"),
"w").write(hrefs.encode("utf8"))
print u"total articles:%s" % count
def auto_publish_article(key):
from common.utils import get_summary_from_html_by_sub
# text = open((u"./txt/%s.txt" % u"【原创】《大雄股市历险记4》股票为什么会上涨").encode("utf8"), "r").read()
# text = get_summary_from_html_by_sub(text, max_num=990000)
# print text
# return
count = 0
hrefs = u""
for index in range(20):
url = 'http://weixin.sogou.com/weixin?query=' + key + '&type=2&ie=utf8&page=' + str(index) + '&p=40040100&dp=1&w=01019900&dr=1'
rep = requests.get(url)
text = rep.text
jq = pq(text)
lst_articles = jq('.wx-rb3 .txt-box a')
for article in lst_articles:
print count
href = article.get("href")
name = article.text_content()
text = requests.get(href).text
text = get_summary_from_html_by_sub(text, max_num=990000, filter_nbsp=True)
re_blank = re.compile('[\s]+', re.I)
key_text = re_blank.sub('', text)
if not 300 < len(key_text) < 3000:
continue
if is_in_baidu(key_text[50:60]):
continue
if is_in_baidu(key_text[150:160]):
continue
if is_in_baidu(key_text[250:260]):
continue
count += 1
hrefs += u"%s\n" % href
open((u"./txt/%s.txt" % name).encode("utf8"), "w").write(text.encode("utf8"))
# break
open((u"./txt/hrefs.txt").encode("utf8"), "w").write(hrefs.encode("utf8"))
print u"total articles:%s" % count
def get_summary(self):
"""
@attention: 通过内容获取摘要
"""
from common import utils
return utils.get_summary_from_html_by_sub(self.content)
def get_summary(self):
"""
@note: 通过内容获取摘要
"""
from common import utils
return utils.get_summary_from_html_by_sub(self.des)
def get_summary(self):
"""
@note: 通过内容获取摘要
"""
from common import utils
return utils.get_summary_from_html_by_sub(self.des)
def get_summary(self):
"""
@attention: 通过内容获取摘要
"""
from common import utils
return utils.get_summary_from_html_by_sub(self.summary)
