def write_new_file(self, url, title, source, i, time):
ok = 0
content = '''
<html>
<head>
<meta charset="utf-8">
<meta name="keywords" content="estarinfo">
<title>''' + title + '''</title>
</head>
<body>
<h1 class="title">''' + title + '''</h1>
<span class="time">''' + time + '''</span>
<span class="source">130679</span>
<div class="article">''' + source + '''</div>
</body>
</html>
'''
page_text = url + '\n' + title + '\n130679\n\n\n\n' + content
if self.debug:
print('count:', self.total, ' === ', title, ' ===')
if '' == self._dir:
self.djckb_mkdir()
filename = self._dir + 'iask_' + str(i) + '_' + str(len(self.d)) + '.htm-2'
for num in range(2):
if 1 == crawlerfun.write_file(filename, page_text, ifdisplay = 0):
fileName = '/root/Downloads/djckb/' + 'iask_' + str(i) + '_' + str(len(self.d)) + '.htm-2'
crawlerfun.write_file(fileName, page_text, ifdisplay = 0) # 再次保存到/root/Downloads目录下
ok = 1
break
else: # 有时目录会被c程序删掉
crawlerfun.mkdir(self._dir)
return ok
def write_new_file(self, url, title, source, i, time, id):
content = '''
<html>
<head>
<meta charset="utf-8">
<meta name="keywords" content="estarinfo">
<title>''' + title + '''</title>
</head>
<body>
<h1 class="title">''' + title + '''</h1>
<span class="time">''' + time + '''</span>
<span class="source">''' + str(id) + '''</span>
<div class="article">''' + source + '''</div>
</body>
</html>
'''
page_text = url + '\n' + title + '\n' + str(id) + '\n\n\n\n' + content
if self.debug:
print('count:', self.i, ' --- ', title)
if '' == self._dir:
self.crawl_mkdir()
filename = self._dir + 'iask_' + str(i) + '_' + str(len(self.d)) + '.htm-2'
for num in range(2):
if 1 == crawlerfun.write_file(filename, page_text, ifdisplay = 0):
break
else: # 有时目录会被c程序删掉
crawlerfun.mkdir(self._dir)
def write_new_file(self, url, title, source, i, time, id):
if self.debug:
print('count:', self.i, ' --- ', title)
content = '''
<html>
<head>
<meta charset="utf-8">
<meta name="keywords" content="estarinfo">
<title>''' + title + '''</title>
</head>
<body>
<h1 class="title">''' + title + '''</h1>
<span class="time">''' + time + '''</span>
<span class="source">''' + str(id) + '''</span>
<div class="article">''' + source + '''</div>
</body>
</html>
'''
page_text = url + '\n' + title + '\n' + str(id) + '\n\n\n\n' + content
if '' == self._dir:
self.jlwb_mkdir()
filename = self._dir + 'iask_' + str(i) + '_' + str(len(
self.d)) + '.htm-2'
for num in range(2):
if 1 == crawlerfun.write_file(filename, page_text, ifdisplay=0):
savePath = '/root/estar_save/jlwb/'
if not os.path.exists(savePath):
os.makedirs(savePath)
fileName = savePath + 'iask_' + str(i) + '_' + str(len(
self.d)) + '.htm-2'
crawlerfun.write_file(fileName, page_text,
ifdisplay=0) # 再次保存到/root/estar_save目录下
break
else: # 有时目录会被c程序删掉
crawlerfun.mkdir(self._dir)
def write_new_file(self, url, title, source, i, id, time):
dct = {1170771: '国家电网有限公司', 1170773: '中国南方电网供应链统一服务平台'}
ok = 0
content = '''
<html>
<head>
<meta charset="utf-8">
<meta name="keywords" content="estarinfo">
</head>
<body>
<h1 class="title">''' + title + '''</h1>
<span class="time">''' + time + '''</span>
<span class="source">''' + dct[id] + '''</span>
<div class="article">''' + source + '''</div>
</body>
</html>
'''
page_text = url + '\n' + title + '\n' + str(id) + '\n\n\n' + content
print(title)
if '' == self._dir:
self.guojiadianwang_mkdir()
filename = self._dir + 'iask_' + str(i) + '_' + str(len(
self.d)) + '.htm-2'
for num in range(2):
if 1 == crawlerfun.write_file(filename, page_text, ifdisplay=0):
filename = '/root/estar_save/' + 'iask_' + str(i) + '_' + str(
len(self.d)) + '.htm-2'
crawlerfun.write_file(filename, page_text,
ifdisplay=0) # 再次保存到/root/estar_save目录下
ok = 1
break
else: # 有时目录会被c程序删掉
crawlerfun.mkdir(self._dir)
return ok
def write_new_file(self, current_url, current_title, page_source, i):
ok = 0
# 合成铱星文件格式
# page_source = current_url + '\n' + current_title + '\n' + '1152937' + '\n\n\n\n' + page_source
page_text = current_url + '\n' + current_title + '\n0\n\n\n\n' + page_source
# iask_3_7830.htm-2 #iask_[ip数字]_[采集文章序号].htm-[线程号]
if '' == self._dir:
self.baijiahao_mkdir()
# filename = self._dir + 'iask_' + str(page) + '_' + str(self.total.num) + '.htm-2'
filename = self._dir + 'iask_' + +str(ts) + '_' + str(i) + '.html'
for num in range(2):
if 1 == crawlerfun.write_file(filename, page_text, ifdisplay=0):
ok = 1
break
else: # 有时目录会被c程序删掉
crawlerfun.mkdir(self._dir)
return ok