import requests
import lxml
from lxml import etree
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36"
}
#拿类别名称
def getcategory(url):
response = requests.get(url,headers=headers)
html = response.content.decode('utf-8')
# print(html)
mytree = lxml.etree.HTML(html)
categoryList = mytree.xpath('/html/body/div[2]/div/div[1]/div[1]/table/tbody/tr[4]/td[2]/a/text()')
categoryList.pop(0)
return categoryList
#拿类别的页数
def getpagenum(url):
response = requests.get(url,headers=headers)
html = response.content.decode('utf-8')
mytree = lxml.etree.HTML(html)
pagenum = mytree.xpath('/html/body/div[2]/div/div[2]/ul/li[last()]/a/@data-ci-pagination-page')[0]
return pagenum
#拿详情页的url
def getpage(url):
pagelist &#
Spider学习笔记(十二):爬取迷你MP4电影信息(翻页数据爬取)
最新推荐文章于 2023-06-27 18:23:08 发布
本文记录了使用Python爬虫进行迷你MP4电影信息的爬取过程,详细讲解了如何处理网页翻页,获取多页数据的关键技巧。通过实例,展示了网络请求和解析HTML的实现细节。
摘要由CSDN通过智能技术生成