# -*- coding: utf-8 -*-
'''把前1000个关键词的搜索结果保存，为以后的搜索调整做对比'''
import time
from libs.parameter import generateEnv
from lnc.search.simple import Simple
simple = Simple(generateEnv('alpha'))
simple.login()
time.sleep(5)
keyword_file = 'input/keywords.txt'
keywords = [unicode(k.strip(), 'utf-8') for k in open(keyword_file, 'r')]
output = open('output/after-adjust.csv', 'a')
b = 1
for keyword in keywords:
res = simple.get_results_list(keyword)
if res:
lines = map(None, (keyword,), (res['total'],), (res['time'],), res['title'])
for l in lines:
line = [x if x is not None else u'' for x in l]
output.write("%s|%s|%s|%s\n" % tuple(line))
output.write("\n")
output.flush()
simple.close(logout=True)
#-*- coding: utf-8 -*-
'''
从input/exact_title.txt文件里面读取标题
然后进行搜索，检查第一条结果是否中标题完全匹配
注意附件的标题会在后面有一个括号，括号里面是附件的文件名
'''
import re, time
from libs.parameter import generateEnv
from lnc.search.simple import Simple
input_titles = [unicode(x.strip(), 'utf-8') for x in open('input/exact_title.txt')]
lnc_simple = Simple(generateEnv('alpha'))
lnc_simple.login()
time.sleep(5)
p = re.compile("\(\d+.[a-zA-Z]{,4}\)", re.IGNORECASE)
output = open('logs/exact_title.csv', 'a')
for it in input_titles:
title_list = lnc_simple.get_results_list(it)
first_equal = False
if title_list:
if len(title_list[0]) > len(it) and title_list[0].find(it) > -1:
remain_title = title_list[0][len(it):].strip()
if p.match(remain_title):
first_equal = True
elif it == title_list[0]: