def start_search(bid, tbw_list):
"""
经过聚类后便可以开始搜索， 进行st().search_topic搜索，生成文件夹，如果不是热点的话题，便删除文件夹
:param bid: 每一个类的代表博文id
:param tbw_list: 这个类的博文相关属性的组合， [(title1,blog1,word1),(title2,blog2,word2)]
:return:
"""
short_dir = create_time_file(tbw_list[0][0]) # 创建标题文件夹
corpus_dir = DOC_DIR + '/' + short_dir + 'uid=' + str(bid) + '.txt'
print "生成的动态目录：", corpus_dir
txt_file = open(corpus_dir, 'w+')
bid_like = 0 # 该bid类的点赞规模
bid_forward = 0
bid_comment = 0
for tbw_tuple in tbw_list: # [(title1,blog1,word1),(title2,blog2,word2)]
print bid, "类的博文标题, 博文, 关键词", tbw_tuple[0], tbw_tuple[1], tbw_tuple[2]
total_result_list, total_reason_list, lfc_all_num = st().search_topic(
bid, tbw_tuple)
# total_result_list = [[博文id,博文时间,标题,博文,关键词,首发者的id,首发者的名字,点赞,转发,评论,origin], ]
for com_index in range(len(total_result_list)):
for com in total_result_list[com_index]:
txt_file.write(str(com) + '\n')
# total_reason_list = [[古阿陌@洗洗睡@人民日报, 南方报@人民日报, yutsfa@人民日报 ], ]
for reason in total_reason_list[com_index]:
print "转发理由：", reason
txt_file.write(str(reason) + '\n')
txt_file.write('\n')
txt_file.write('\n\n\n--------------------\n')
# lfc_all_num = [该话题的点赞规模,该话题的转发规模,该话题的评论规模]
print '*******************************'
print "该话题的点赞规模", lfc_all_num[0]
print "该话题的转发规模", lfc_all_num[1]
print "该话题的评论规模", lfc_all_num[2]
bid_like += int(lfc_all_num[0])
bid_forward += int(lfc_all_num[1])
bid_comment += int(lfc_all_num[2])
print tbw_list[0][0], '聚合的类的话题规模', bid_like, bid_forward, bid_comment
txt_file.write(
str(bid_like) + '\n' + str(bid_forward) + '\n' + str(bid_comment) +
'\n')
txt_file.close()
if bid_like + bid_forward + bid_comment == 0:
deleted_dir = DOC_DIR + '/' + 'topic' + '/' + tbw_list[0][0]
print "不是热点的文件夹删除", deleted_dir
shutil.rmtree(deleted_dir)
def start_search(bid, tbw_list):
"""
经过聚类后便可以开始搜索， 进行st().search_topic搜索，生成文件夹，如果不是热点的话题，便删除文件夹
:param bid: 每一个类的代表博文id
:param tbw_list: 这个类的博文相关属性的组合， [(title1,blog1,word1),(title2,blog2,word2)]
:return:
"""
short_dir = create_time_file(tbw_list[0][0]) # 创建标题文件夹
corpus_dir = DOC_DIR + '/' + short_dir + 'uid=' + str(bid) + '.txt'
print "生成的动态目录：", corpus_dir
txt_file = open(corpus_dir, 'w+')
bid_like = 0 # 该bid类的点赞规模
bid_forward = 0
bid_comment = 0
for tbw_tuple in tbw_list: # [(title1,blog1,word1),(title2,blog2,word2)]
print bid, "类的博文标题, 博文, 关键词", tbw_tuple[0], tbw_tuple[1], tbw_tuple[2]
total_result_list, total_reason_list, lfc_all_num = st().search_topic(bid, tbw_tuple)
# total_result_list = [[博文id,博文时间,标题,博文,关键词,首发者的id,首发者的名字,点赞,转发,评论,origin], ]
for com_index in range(len(total_result_list)):
for com in total_result_list[com_index]:
txt_file.write(str(com) + '\n')
# total_reason_list = [[古阿陌@洗洗睡@人民日报, 南方报@人民日报, yutsfa@人民日报 ], ]
for reason in total_reason_list[com_index]:
print "转发理由：", reason
txt_file.write(str(reason) + '\n')
txt_file.write('\n')
txt_file.write('\n\n\n--------------------\n')
# lfc_all_num = [该话题的点赞规模,该话题的转发规模,该话题的评论规模]
print '*******************************'
print "该话题的点赞规模", lfc_all_num[0]
print "该话题的转发规模", lfc_all_num[1]
print "该话题的评论规模", lfc_all_num[2]
bid_like += int(lfc_all_num[0])
bid_forward += int(lfc_all_num[1])
bid_comment += int(lfc_all_num[2])
print tbw_list[0][0], '聚合的类的话题规模', bid_like, bid_forward, bid_comment
txt_file.write(str(bid_like) + '\n' +
str(bid_forward) + '\n' +
str(bid_comment) + '\n')
txt_file.close()
if bid_like + bid_forward + bid_comment == 0:
deleted_dir = DOC_DIR + '/' + 'topic' + '/' + tbw_list[0][0]
print "不是热点的文件夹删除", deleted_dir
shutil.rmtree(deleted_dir)
def start_search(time_dir,one_blog):
"""
对一个博文在微博平台进行搜索
:return:
"""
total_dir = create_topic_file(time_dir, one_blog)
print total_dir
print "正在进行搜索并爬取..."
# [blog_id, ptime, topic, content, user_id, user_name,like_num, rpt_num, cmt_num]
total_result_list, total_reason_list, total_comment_list, total_participants_list, total_originator, lfc_all_num = st().search_topic(one_blog)
# 写入内容
write_forward(total_dir, total_reason_list)
write_comment(total_dir, total_comment_list)
write_participants(total_dir, total_participants_list)
# lfc_all_num = [该话题的点赞规模,该话题的转发规模,该话题的评论规模]
print '*******************************'
print "该话题的点赞规模", lfc_all_num[0]
print "该话题的转发规模", lfc_all_num[1]
print "该话题的评论规模", lfc_all_num[2]
blog_id = total_result_list[0]
content = total_result_list[3]
post_time = total_result_list[1]
comment_num = lfc_all_num[2]
like_num = lfc_all_num[0]
repost_num = lfc_all_num[1]
result_dict.setdefault(one_blog,[blog_id,content,total_originator,post_time,comment_num,repost_num,like_num])
def start_search(one_blog, event_name):
"""
对一个博文在微博平台进行搜索
:return:
"""
time_dir = create_time_file()
event_news = event_name+'/'+one_blog
total_dir = create_topic_file(event_news, time_dir)
print total_dir
print "正在进行搜索并爬取..."
total_result_list, total_reason_list, total_comment_list, total_participants_list = st().search_topic(one_blog)
if len(total_result_list) > 0:
# 写入内容
write_forward(total_dir, total_reason_list)
write_comment(total_dir, total_comment_list)
write_participants(total_dir, total_participants_list)
# [[blog_id, content, user_name, user_id, ptime, topic, like_num, rpt_num, cmt_num]]
blog_id = total_result_list[0][0]
content = total_result_list[0][1]
originator = total_result_list[0][2]
originator_id = total_result_list[0][3]
post_time = total_result_list[0][4]
topic = total_result_list[0][5]
like_num = total_result_list[0][6]
repost_num = total_result_list[0][7]
comment_num = total_result_list[0][8]
print "博文id ", blog_id
print "博文内容 ", content
print "发源者昵称 ", originator
print "发源者id ", originator_id
print "发表时间 ", post_time
print "话题 ", topic
print "点赞数 ", like_num
print "转发数 ", repost_num
print "评论数 ", comment_num
total_result_list[0].append(total_dir)
result_dict.setdefault(one_blog, total_result_list[0])
# [blog_id,content,originator,originator_id,post_time,topic,like_num,repost_num,comment_num,total_dir])
else:
print "爬取失败"
def start_search(bid, tbw_list):
"""
经过聚类后便可以开始搜索， 进行st().search_topic搜索，生成文件夹，如果不是热点的话题，便删除文件夹
:param bid: 每一个类的代表博文id
:param tbw_list: 这个类的博文相关属性的组合， [(title1,blog1,word1),(title2,blog2,word2)]
:return:
"""
db = Database()
eve = Event()
con = Content()
e_id = 'tp' + bid
short_dir = create_time_file(tbw_list[0][0]) # 创建标题文件夹
corpus_dir = DOC_DIR + '/' + short_dir + 'uid=' + str(bid) + '.txt'
# print "生成的动态目录：", corpus_dir
txt_file = open(corpus_dir, 'w+')
bid_like = 0 # 该bid类的点赞规模
bid_forward = 0
bid_comment = 0
for tbw_tuple in tbw_list: # [(title1,blog1,word1),(title2,blog2,word2)]
# print bid, "类的博文标题, 博文, 关键词", tbw_tuple[0], tbw_tuple[1], tbw_tuple[2]
total_result_list, total_reason_list, lfc_all_num = st().search_topic(bid, tbw_tuple)
# total_result_list = [[博文id,博文时间,标题,博文,关键词,首发者的id,首发者的名字,点赞,转发,评论,origin], ]
for com_index in range(len(total_result_list)):
# for com in total_result_list[com_index]:
# txt_file.write(str(com) + '\n')
# total_reason_list = [[古阿陌@洗洗睡@人民日报, 南方报@人民日报, yutsfa@人民日报 ], ]
for reason in total_reason_list[com_index]:
# print "转发理由：", reason
txt_file.write(str(reason) + '\n')
# txt_file.write('\n')
# txt_file.write('\n\n\n--------------------\n')
# lfc_all_num = [该话题的点赞规模,该话题的转发规模,该话题的评论规模]
# print '*******************************'
# print "该话题的点赞规模", lfc_all_num[0]
# print "该话题的转发规模", lfc_all_num[1]
# print "该话题的评论规模", lfc_all_num[2]
bid_like += int(lfc_all_num[0])
bid_forward += int(lfc_all_num[1])
bid_comment += int(lfc_all_num[2])
print '*******************************'
print tbw_list[0][0], '***聚合的类的话题规模***', bid_like, bid_forward, bid_comment
# txt_file.write(str(bid_like) + '\n' +
# str(bid_forward) + '\n' +
# str(bid_comment) + '\n')
txt_file.close()
if bid_like + bid_forward + bid_comment == 0:
deleted_dir = DOC_DIR + '/' + 'topic' + '/' + tbw_list[0][0]
pic_dir = deleted_dir.replace('documents','static/sna')
print "不是热点的文件夹删除", deleted_dir
shutil.rmtree(deleted_dir)
shutil.rmtree(pic_dir)
eve.delete_event(e_id)
else:
# now = datetime.datetime.now()
# other_style_time = now.strftime("%Y-%m-%d %H:%M:%S")
# 存 interface_networkscale()和increment:
main_network(DOC_DIR+'/'+short_dir)
corpus_dir = short_dir + 'uid=' + str(bid) + '.txt'
label_dir = short_dir + 'new_label_link.xls'
sna_dir = 'sna/'+ short_dir + 'SNA.png'
print 'label!!!!!!', DOC_DIR+'/'+label_dir
if os.path.exists(DOC_DIR+'/'+label_dir):
print 'yep'
try:
leader = find_leader(label_dir)
db.save_network_scale(e_id, corpus_dir, label_dir,sna_dir, leader)
db.save_increment(e_id, bid_comment,bid_forward, bid_like)
except:
leader = 'Unknown'
db.save_network_scale(e_id, corpus_dir, label_dir,sna_dir, leader)
db.save_increment(e_id, bid_comment,bid_forward, bid_like)
else:
print 'nope'
label_dir = 'None'
sna_dir = 'None'
leader = 'Unknown'
db.save_network_scale(e_id, corpus_dir, label_dir,sna_dir, leader)
db.save_increment(e_id, bid_comment,bid_forward, bid_like)
print "storing!!!"
def start_search(time_dir, one_blog):
"""
对一个博文在微博平台进行搜索
:return:
"""
total_dir = create_topic_file(time_dir, one_blog)
print total_dir
print "正在进行搜索并爬取..."
total_result_list, total_reason_list, total_comment_list, total_participants_list = st(
).search_topic(one_blog)
if len(total_result_list) > 0:
# 写入内容
write_forward(total_dir, total_reason_list)
write_comment(total_dir, total_comment_list)
write_participants(total_dir, total_participants_list)
# [[blog_id, content, user_name, user_id, ptime, topic, like_num, rpt_num, cmt_num]]
blog_id = total_result_list[0][0]
content = total_result_list[0][1]
originator = total_result_list[0][2]
originator_id = total_result_list[0][3]
post_time = total_result_list[0][4]
like_num = total_result_list[0][5]
repost_num = total_result_list[0][6]
comment_num = total_result_list[0][7]
print "博文id ", blog_id
print "博文内容 ", content
print "发源者昵称 ", originator
print "发源者id ", originator_id
print "发表时间 ", post_time
print "点赞数 ", like_num
print "转发数 ", repost_num
print "评论数 ", comment_num
result_dict.setdefault(one_blog, total_result_list[0])
# [blog_id,content,originator,originator_id,post_time,like_num,repost_num,comment_num])
else:
print "爬取失败"
def start_search(time_dir, one_blog):
"""
对一个博文在微博平台进行搜索
:return:
"""
total_dir = create_topic_file(time_dir, one_blog)
print total_dir
print "正在进行搜索并爬取..."
# [blog_id, ptime, topic, content, user_id, user_name,like_num, rpt_num, cmt_num]
total_result_list, total_reason_list, total_comment_list, total_participants_list, total_originator, lfc_all_num = st(
).search_topic(one_blog)
# 写入内容
write_forward(total_dir, total_reason_list)
write_comment(total_dir, total_comment_list)
write_participants(total_dir, total_participants_list)
# lfc_all_num = [该话题的点赞规模,该话题的转发规模,该话题的评论规模]
print '*******************************'
print "该话题的点赞规模", lfc_all_num[0]
print "该话题的转发规模", lfc_all_num[1]
print "该话题的评论规模", lfc_all_num[2]
blog_id = total_result_list[0]
content = total_result_list[3]
post_time = total_result_list[1]
comment_num = lfc_all_num[2]
like_num = lfc_all_num[0]
repost_num = lfc_all_num[1]
result_dict.setdefault(one_blog, [
blog_id, content, total_originator, post_time, comment_num, repost_num,
like_num
])
def start_search(bid, tbw_list):
"""
经过聚类后便可以开始搜索， 进行st().search_topic搜索，生成文件夹，如果不是热点的话题，便删除文件夹
:param bid: 每一个类的代表博文id
:param tbw_list: 这个类的博文相关属性的组合， [(title1,blog1,word1),(title2,blog2,word2)]
:return:
"""
e_id = "tp" + bid
short_dir = create_time_file(tbw_list[0][0]) # 创建标题文件夹
corpus_dir = DOC_DIR + "/" + short_dir + "uid=" + str(bid) + ".txt"
print "生成的动态目录：", corpus_dir
txt_file = open(corpus_dir, "w+")
bid_like = 0 # 该bid类的点赞规模
bid_forward = 0
bid_comment = 0
for tbw_tuple in tbw_list: # [(title1,blog1,word1),(title2,blog2,word2)]
print bid, "类的博文标题, 博文, 关键词", tbw_tuple[0], tbw_tuple[1], tbw_tuple[2]
total_result_list, total_reason_list, lfc_all_num = st().search_topic(bid, tbw_tuple)
# total_result_list = [[博文id,博文时间,标题,博文,关键词,首发者的id,首发者的名字,点赞,转发,评论,origin], ]
for com_index in range(len(total_result_list)):
for com in total_result_list[com_index]:
txt_file.write(str(com) + "\n")
# total_reason_list = [[古阿陌@洗洗睡@人民日报, 南方报@人民日报, yutsfa@人民日报 ], ]
for reason in total_reason_list[com_index]:
print "转发理由：", reason
txt_file.write(str(reason) + "\n")
txt_file.write("\n")
txt_file.write("\n\n\n--------------------\n")
# lfc_all_num = [该话题的点赞规模,该话题的转发规模,该话题的评论规模]
print "*******************************"
print "该话题的点赞规模", lfc_all_num[0]
print "该话题的转发规模", lfc_all_num[1]
print "该话题的评论规模", lfc_all_num[2]
bid_like += int(lfc_all_num[0])
bid_forward += int(lfc_all_num[1])
bid_comment += int(lfc_all_num[2])
print tbw_list[0][0], "聚合的类的话题规模", bid_like, bid_forward, bid_comment
txt_file.write(str(bid_like) + "\n" + str(bid_forward) + "\n" + str(bid_comment) + "\n")
txt_file.close()
if bid_like + bid_forward + bid_comment == 0:
deleted_dir = DOC_DIR + "/" + "topic" + "/" + tbw_list[0][0]
print "不是热点的文件夹删除", deleted_dir
shutil.rmtree(deleted_dir)
else:
now = datetime.datetime.now()
other_style_time = now.strftime("%Y-%m-%d %H:%M:%S")
# 存 interface_networkscale():
event_id = e_id
corpus_dir = short_dir
label_dir = label路径
sna_dir = sna图的路径, 这个你可以留空
leader = 留空
# 存 interface_increment():
check_time = other_style_time
comment_num = bid_comment
repost_num = bid_forward
like_num = bid_like