def qingqiu(self):
links_list = []
i = 1
x = '//div[@class="paginationControl"]/preceding-sibling::ul//a'
print('开始请求一级页面.....')
while True:
html = ktgg.request(self.url, i)
# 判断请求是超过了页面总数
l = re.findall('上一页', html)
if l == []:
break
# xpath匹配出链接和文本
links = ktgg.parse(html, x)
links_list.extend(links)
i += 1
print('请求到详情页数量是: ' + str(len(links_list)))
return links_list
def qingqiu(self):
links_list = []
i = 1
x = '//div[@id="list"]//li/span/a'
print('开始请求一级页面.....')
while True:
html = ktgg.request(self.url, i)
# 判断请求是超过了页面总数
l = re.findall('上一页', html)
if l == []:
break
# xpath匹配出链接和文本
links = ktgg.parse(html, x)
links_list.extend(links)
i += 1
print('请求到详情页数量是: ' + str(len(links_list)))
return links_list