def move_article_and_image():
article_id_sql = "SELECT DISTINCT article_id from t_article_status"
target_school_article_sql = "SELECT id FROM t_article WHERE origin = \"中国政法大学\""
result = DBUtil.select_datas(article_id_sql)
target_result = DBUtil.select_datas(target_school_article_sql)
for item in target_result:
result.append(item)
image_path = "/data/who_focus/image/"
article_path = "/home/jfqiao/wechat_articles/"
for item in result:
sql = "SELECT url, image_url FROM t_article WHERE id=%s" % item[
"article_id"]
article = DBUtil.select_data(sql)
article_file_name = article["url"].replace("/", "").replace(":", "")
os.system("cp \"%s\" /home/jfqiao/tmp_article/" %
(article_path + article_file_name))
os.system("cp \"%s\" /home/jfqiao/tmp_article/" %
(article_path + article_file_name + "_abstract"))
if article["image_url"].startswith("https://mmbiz.qpic") or article[
"image_url"].startswith("http://mmbiz.qpic"):
continue
pos = article["image_url"].find("?")
if pos == -1:
pos = len(article["image_url"])
image_file_name = article["image_url"][:pos].replace(":", "").replace(
"/", "")
os.system("cp \"%s\" /home/jfqiao/tmp_image/" %
(image_path + image_file_name))
os.system("cp \"%s\" /home/jfqiao/tmp_image/" %
(image_path + image_file_name + ".txt"))
def get_article_info(date_str):
"""
查询publish_time在一定的时间之后的文章ID
:param date_str: 给定的时间字符串，格式为 yyyy-mm-dd HH:MM:SS.
:return: 返回的结果是一个list，其中每一项都是dict，利用列的名字进行索引即可。
"""
sql = "SELECT id, url, image_url FROM t_article WHERE publish_time <= \"%s\"" % date_str
result = DBUtil.select_datas(sql)
return result
