|
马上注册,结交更多好友,享用更多功能^_^
您需要 登录 才可以下载或查看,没有账号?立即注册
x
用xpath抓数据,在浏览器上显示能抓到,但是到Python里面返回空列表的情况吗
all_url的值是空
import requests
from fake_useragent import UserAgent
from lxml import etree
def get_html(index_url):
headers={
"User-Agent":UserAgent().chrome
}
resp=requests.get(index_url,headers=headers)
resp.encoding='gbk'
if resp.status_code==200:
return resp.text
else:
return None
def parse_index(html):
e=etree.HTML(html)
all_url=e.xpath('//div[@class="channel-detail movie-item-title"]/a/@href')
return ['https://maoyan.com{}'.format(url)for url in all_url]
def main():
index_url="https://maoyan.com/films"
html=get_html(index_url)
moive_url=parse_index(html)
print(moive_url)
if __name__ == '__main__':
main() |
|