- it技术
- 爬虫xpath作业
import requests
import os
from lxml
import etree
if not os
.path
.exists
('./download'):
os
.makedirs
('./download')
headers
= {
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.103 Safari/537.36'
}
url
= 'http://aspx.sc.chinaz.com/query.aspx?keyword=%E5%85%8D%E8%B4%B9&issale=&classID=864&page=1'
page_text
= requests
.get
(url
=url
, headers
=headers
).text
tree
= etree
.HTML
(page_text
)
downloadpage_url
= tree
.xpath
('//div[@id="main"]/div/div/a/@href')
rar_name
= tree
.xpath
('//div[@id="main"]/div/div/a/img/@alt')
for i
in range(0,5):
downloadpage_text
= requests
.get
(url
=downloadpage_url
[i
], headers
=headers
).text
downloadpage_tree
= etree
.HTML
(downloadpage_text
)
download_url
= downloadpage_tree
.xpath
('//div[@class="clearfix mt20 downlist"]/ul/li[1]/a/@href')[0]
download
= requests
.get
(url
=download_url
, headers
=headers
).content
file_path
= './download/' + rar_name
[i
] + '.rar'
with open(file_path
, 'wb') as fp
:
fp
.write
(download
)
print(rar_name
[i
], '下载成功！')
