def operate_cxjg_page(self,list_string,similar_partno,hc):
'''
处理查询结果页面 有精确匹配 精确匹配页面代码附加在list_string中；否则 相似页面url、partno附加在similar_partno中
参数: list_string: 保存每个digikey搜索型号对应精确页面的代码,格式[hc0,hc1...]
similar_partno: 相似页面url 型号信息,格式[[url,partno],...]
hc: 当前处理页面的代码
'''
res_url_partno = self.p_url_partno.findall(hc)
for url,partno in res_url_partno:
if partno == self.mmp:
url_info = get_url_whole(self.url_search, url)
if debug: print url,partno
self.list_url_exact.append(url_info)
##################
#print "in operate_cxjg_page:",url_info
temp = gethtml(url_info)
if temp is None:
temp = ''
hc_info = filter_html(temp)
##################
if hc_info != 'timeout':
self.list_string.append(hc_info)
else:
''' 型号不精确 相似而已 '''
similar_partno.append([get_url_whole(self.url_search, url), partno])
def get_list_string_mmp(self):
""" 不需要进入详细信息页面，只需要在查询结果页面获取即可 """
__dc__ = 'find the correct pageurl and get the correct pagestring of this correct pageurl'
fun = 'function get_list_string_mmp of %s' % self.name
self.list_string = []
self.similar_partno = []
tishi = u'in %s ' % fun
if self.boolean_iu:
''' 用详细信息页面作为搜索条件 '''
tishi += u'\n查询页面: %s ' % self.info_url
###################
#print "用详细信息页面作为搜索条件",self.info_url
temp = gethtml(self.info_url)
if temp is None:
temp = ''
self.string = filter_html(temp)
###################
self.hc_cxym = self.string
if self.string == 'timeout':
tishi += u'\n 页面超时 '
self.list_string = ['timeout','timeout']
elif self.p_xxxx.findall(self.string):
tishi += u'\n 页面正常进入详细信息页面 '
self.list_string = ['exact',self.string]
self.list_url_exact.append(self.url_search)
else:
tishi += u'\n 页面异常 原本应该正常进入详细信息页面 '
self.list_string = [None,self.string]
''' 直接返回 不执行下述步骤 '''
if debug: print tishi
return self.list_string
###########################
#print "in get_list_string_mmp",self.url_search
temp = gethtml(self.url_search)
if temp is None:
temp = ''
self.string = filter_html(temp)
###########################
self.hc_cxym = self.string
tishi += u'\n查询页面: %s ' % self.url_search
if self.string == 'timeout':
tishi += u'\n 页面超时'
self.list_string = ['timeout','timeout']
elif self.p_cxjg.findall(self.string):
""" 处于 1 查询结果页面；"""
tishi += u'\n 进入查询结果页面 '
''' 处理表格页面中的两种情况: 1 精确 2 相似 '''
self.operate_cxjg_page(self.list_string,self.similar_partno,self.string)
if self.list_string:
count_exact,count_similar = len(self.list_string),0
self.list_string.insert(0,'exact')
else:
count_exact,count_similar = 0,len(self.similar_partno)
self.list_string = ['similar',self.string,self.similar_partno]
tishi += u'\n 得到 %s 个精确匹配页面 %s 个相似型号页面 ' % (count_exact,count_similar)
elif self.p_xxxx.findall(self.string):
""" 只有一个查询结果，查询结果页面跳转至详细信息页面 """
tishi += u'\n 进入详细信息页面 '
self.list_string = ['exact',self.string]
self.list_url_exact.append(self.url_search)
elif self.p_wjg.findall(self.string):
""" 处于 3 提示无结果页面 """
tishi += u'\n 进入无结果页面 '
self.list_string = ['no_result',self.string]
elif self.p_jgfl.findall(self.string):
''' 处于结果分类页面 十分麻烦 '''
tishi += u'\n 进入结果分类页面 '
res_jgfl_url_count = self.p_jgfl_url_count.findall(self.string)
for jgfl_url,jgfl_count in res_jgfl_url_count:
url_whole = get_url_whole(self.url_search,jgfl_url)
#####################
#print "i处于结果分类页面",url_whole
temp = gethtml(url_whole)
if temp is None:
temp = ''
hc = filter_html(temp)
#####################
if int(jgfl_count) == 1:
''' 进入详细信息页面 '''
if str('>%s<' % self.mmp) in hc:
self.list_url_exact.append(url_whole)
self.list_string.append(hc)
else:
''' 进入表格页面 '''
''' 处理表格页面中的两种情况: 1 精确 2 相似 '''
self.operate_cxjg_page(self.list_string,self.similar_partno,hc)
if self.list_string:
count_exact,count_similar = len(self.list_string),0
self.list_string.insert(0,'exact')
else:
count_exact,count_similar = 0,len(self.similar_partno)
self.list_string = ['similar',self.string,self.similar_partno]
tishi += u'\n 得到 %s 个精确匹配页面 %s 个相似型号页面 ' % (count_exact,count_similar)
else:
tishi += u'\n 发生异常 进入未知页面 '
self.list_string = [None,self.string]
if debug: print tishi
return self.list_string