def get_data(self, resp):
'''取：解析数据'''
'''{"name": "??",
"detail_url":"http://www.dachenglaw.com/cn/professionals/qi.ao.html",
"email": "*****@*****.**",
"position":"?????",
"location": "??"}'''
if not resp:
# print(f"请求[{resp.url}],响应为空，不做解析")
return
html = etree.HTML(resp.content.decode())
trs = html.xpath('//tbody/tr')
items = []
for tr in trs:
name = tr.xpath('./td[1]/a/text()')
detail_url = 'http://www.dachenglaw.com' + extra_first(
tr.xpath('./td[1]/a/@href'))
email = tr.xpath('./td[2]/text()')
position = tr.xpath('./td[3]/text()')
location = tr.xpath('./td[4]/text()')
''''''
#print(name,detail_url,email,position,location)
item = {
"name": extra_first(name),
"detail_url": detail_url,
"email": extra_first(email),
"position": extra_first(position),
"location": ''.join(extra_first(location).split())
}
yield item
def get_data(self, resp):
if not resp:
# print(f'请求[{resp.url}],响应为空，不做解析')
return
html = etree.HTML(resp.content.decode())
lis = html.xpath('//div[@class="pc_temp_songlist "]/ul/li')
# print(len(lis))
for ll in lis:
id = ll.xpath("./span[3]/text()")
title = ll.xpath("./@title")
detail_url = ll.xpath("./a/@href")
time = ll.xpath("./span[4]/span/text()")
item = {
"id": extra_first(id),
"title": extra_first(title),
"detail_url": extra_first(detail_url),
"time": extra_first(time),
}
yield item
def get_data(self, resp):
if not resp:
# print(f'请求[{resp.url}],响应为空，不做解析')
return
html = etree.HTML(resp.content.decode())
tables = html.xpath('//div/table')
# print(len(dds))
for table in tables[1:]:
title = table.xpath("./tr/td[2]/div/a/text()")
detail_url = table.xpath("./tr/td[2]/div/a/@href")
info = table.xpath("./tr/td[2]/p/text()")
score = table.xpath("./tr/td[2]/div[2]/span[2]/text()")
desc = table.xpath('./tr/td[2]/p[2]/text()')
item = {
"title": extra_first(title),
"detail_url": extra_first(detail_url),
"info": extra_first(info),
"score": extra_first(score),
"desc": extra_first(desc),
}
yield item
def get_data(self, resp):
if not resp:
return
html = etree.HTML(resp.content.decode())
trs = html.xpath('//dl/dd')
items = []
for i in trs:
id = i.xpath('./i/text()')
title = i.xpath('./a/@title')
detail_url = i.xpath('./a/@href')
actors = i.xpath('./div/div/div/p[2]/text()')
releasetime = i.xpath('./div/div/div/p[3]/text()')
score1 = i.xpath('./div/div/div[2]/p/i[1]/text()')
score2 = i.xpath('./div/div/div[2]/p/i[2]/text()')
item = {
"id": extra_first(id),
"detail_url": 'https://maoyan.com' + extra_first(detail_url),
"title": extra_first(title),
"actors": extra_first(actors),
"releasetime": extra_first(releasetime),
"score": extra_first(score1) + extra_first(score2)
}
yield item
def get_data(self, resp):
if not resp:
# print(f'请求[{resp.url}],响应为空，不做解析')
return
html = etree.HTML(resp.content.decode())
lis = html.xpath('//ol/li')
# print(len(lis))
for li in lis:
id = li.xpath("./div/div/em/text()")
title = li.xpath("./div/div/a/img/@alt")
detail_url = li.xpath("./div/div/a/@href")
content = li.xpath("./div/div[2]/div[2]/p/text()")
score = li.xpath("./div/div[2]/div[2]/div/span[2]/text()")
info = li.xpath('./div/div[2]/div[2]/p/span/text()')
item = {
"id": extra_first(id),
"title": extra_first(title),
"detail_url": extra_first(detail_url),
"content": extra_first(content),
"score": extra_first(score),
"info": extra_first(info),
}
yield item