def ask_detail_discuss(self):
driver = self.driver
item = driver.find_element_by_id(
'comments').find_elements_by_class_name('item')
time.sleep(3)
actual = list()
for i in item:
if i.text != '': # 这里标签有重复，去除哪些没得内容的，不要坑我
ava = i.find_element_by_tag_name('a').get_attribute(
'href').split('dynmsg/')[-1] # 动态链接
nick_name = i.find_element_by_class_name('u-name').text # 昵称
date_publish = i.find_element_by_class_name(
'u-datetime').text # 发布日期
content = i.find_element_by_class_name(
'zy_shou11').text.replace(' ', '') # 发布内容
count = i.find_element_by_class_name(
'icon-label-text').text # 点赞数
actual.append((ava, nick_name, date_publish, content, count))
driver.close()
expect = select(sqls.ask_discuss.replace('lilang_id', self.ask_id))
expect = list(expect)
for i in range(len(expect)):
expect[i] = list(expect[i])
expect[i][2] = time_deal(expect[i][2])
expect[i][3] = pq(content_deal(expect[i][3])).text().replace(
' ', '')
actual = actual if actual else ['null']
expect = expect if expect else ['null']
equal('ask_detail_discuss', expect, actual)
def ask_detail_base_info(self):
driver = self.driver
actual = list()
main = driver.find_element_by_class_name('QA-text-box') # 获取详情主体框
title = main.find_element_by_tag_name('h1').text # 问答标题
content = main.find_element_by_class_name('QA-text-main').text # 问答内容
tags = main.find_element_by_class_name('hot-tag-group').text # 问答标签
nick_name = main.find_element_by_class_name('u-name').text # 发布人昵称
publish_date = main.find_element_by_class_name(
'u-datetime').text # 发布日期
forward_count = main.find_element_by_class_name(
'praise-btn').text.split()[-1] # 点赞数
collect_count = main.find_element_by_class_name(
'u-collect').text.split()[-1] # 收藏数
review_count = main.find_element_by_class_name('u-view').text.split()[
-1] # 浏览数
time.sleep(3)
driver.close()
actual.append((title, content, tags, nick_name, publish_date,
forward_count, collect_count, review_count))
expect = select(
sqls.ask_detail_base_info.replace('lilang_id', self.ask_id))
expect = list(expect)
for i in range(len(expect)):
expect[i] = list(expect[i])
expect[i][1] = pq(content_deal(expect[i][1])).text()
expect[i][2] = expect[i][2].replace(',', ' ')
expect[i][4] = time_deal(expect[i][4])
expect[i][7] -= 1
equal('ask_detail_base_info', expect, actual)
def ask_detail_course_ask_base_info(self):
driver = self.driver
actual = list()
main = driver.find_element_by_class_name('QA-text-box') # 获取详情主体框
title = main.find_element_by_tag_name('h1').text # 问答标题
content = main.find_element_by_class_name('QA-text-main').text.replace(
'\n', '').replace(' ', '') # 问答内容
tags = main.find_element_by_class_name('hot-tag-group').text # 问答标签
source = main.find_element_by_class_name('art_zy_edit').text.split(
'源自：')[-1] # 源自
nick_name = main.find_element_by_class_name('u-name').text # 发布人昵称
publish_date = main.find_element_by_class_name(
'u-datetime').text # 发布日期
forward_count = main.find_element_by_xpath(
'/html/body/div[9]/div[5]/div/div/div[1]/div/'
'div[1]/div[3]/div[2]/span[2]').text # 点赞数
collect_count = main.find_element_by_class_name(
'u-collect').text.split()[-1] # 收藏数
review_count = main.find_element_by_class_name('u-view').text.split()[
-1] # 浏览数
time.sleep(3)
driver.close()
actual.append((title, content, tags, source, nick_name, publish_date,
forward_count, collect_count, review_count))
expect = select(
sqls.ask_detail_course_ask_base_info.replace(
'lilang_id', self.ask_id))
expect = list(expect)
for i in range(len(expect)):
expect[i] = list(expect[i])
expect[i][1] = pq(content_deal(expect[i][1])).text().replace(
' ', '')
expect[i][5] = time_deal(expect[i][5])
expect[i][8] -= 1
equal('ask_detail_course_ask_base_info', expect, actual)
def article_list_expect(self, article_type):
expect = select(sqls.article_list.replace('lilang_type', article_type))
expect = list(expect)
for i in range(len(expect)):
expect[i] = list(expect[i])
expect[i][2] = pq(content_deal(expect[i][2])).text()[0:49]
expect[i][3] = pq(content_deal(expect[i][3])).text().replace(
' ', '').replace(u'\xa0', '')[0:80]
expect[i][4] = expect[i][4].replace(',',
'') if expect[i][4] else ''
expect[i][8] = time_deal(expect[i][8])
return expect
def ask_list(self):
item = self.txt('.QA-list>.item')
actual = list()
for i in item:
i = pq(i)
ava = i('.col-left').find('img').attr('src').split('uploads/')[
-1] # 头像地址
nick_name = i('.u-name').text() # 昵称
title = i('.col-right h3>a').text() # 问答标题
reply = i('.item-r-A').text().split('[最新回答]')[-1].replace(
' 查看详细', '')[0:100] # 最新回复
tags = i('.hot-tag-group .hot-tag').text() # 问答标签
tags = tags if tags else None
source = i('.hot-tag-group .from-where').text().split('源自： ')[
-1] # 源自xx
date_publish = i('.datetime').text() # 发布时间
review_count = i('.icon-browse').text() # 浏览数
reply_count = i('.icon-ask').text() # 回复数
forward_count = i('.icon-good').text() # 点赞数
actual.append(
(ava, nick_name, title, reply, tags, source, date_publish,
review_count, reply_count, forward_count))
self.driver.close()
expect = select(sqls.ask_list)
expect = list(expect)
for i in range(len(expect)):
expect[i] = list(expect[i])
expect[i][2] = pq(content_deal(expect[i][2])).text()[0:49]
print i, expect[i][3]
expect[i][3] = expect[i][3] if expect[i][3] else u'还没有人回答这个问题呢...'
expect[i][3] = pq(content_deal(expect[i][3])).text()[0:100]
expect[i][4] = expect[i][4].replace(
',', '') if expect[i][4] else expect[i][4]
expect[i][6] = time_deal(expect[i][6])
equal('ask_list', expect, actual)