# 匹配评论
pattern6 = re.compile('<div id="review_.*?" class="reviewSelector.*?<!--etk-->', re.S)
# 获得所有的评论
items6 = re.findall(pattern6, html)
# 遍历分析每一个评论内容
for item in items6:
# 获取用户的主页地址 http://www.tripadvisor.cn/members/打头
p6_user_url ='href="members/(.*?)"'
user_url = re.search().group()
print(user_url)
# 评论标题
p6_rv_title = '<span class="noQuotes">(.*?)</span>'
rv_title = re.search().group()
# 评分
p6_rv_rate = '<img class="sprite-rating_s_fill.*?alt=[0-9]分'
rv_rate = re.search().group()
# 发表时间
p6_rv_time = '<span class="ratingDate">(.*?)</span>'
rv_time = re.search().group()
# 评论内容
p6_rv_content = '<p class="partial_entry">(.*?)</p>'
rv_content = re.search().group()
pattern6 = re.compile('<div id="review_.*?" class="reviewSelector.*?<!--etk-->', re.S)
# 获得所有的评论
items6 = re.findall(pattern6, html)
# 遍历分析每一个评论内容
for item in items6:
# 获取用户的主页地址 http://www.tripadvisor.cn/members/打头
p6_user_url ='href="members/(.*?)"'
user_url = re.search().group()
print(user_url)
# 评论标题
p6_rv_title = '<span class="noQuotes">(.*?)</span>'
rv_title = re.search().group()
# 评分
p6_rv_rate = '<img class="sprite-rating_s_fill.*?alt=[0-9]分'
rv_rate = re.search().group()
# 发表时间
p6_rv_time = '<span class="ratingDate">(.*?)</span>'
rv_time = re.search().group()
# 评论内容
p6_rv_content = '<p class="partial_entry">(.*?)</p>'
rv_content = re.search().group()