小小外星人国语,梅苏特·厄齐尔,美女白山馆
from requests_html import htmlsession session =htmlsession() #https://www.flipkart.com/lc/getdata?datasourceid=websitenavigationmenuds_1.0 #还有个t参数,目前可以不加 res =session.get('https://www.flipkart.com/lc/getdata?datasourceid=websitenavigationmenuds_1.0', verify=false) appliances_columns_list=res.json().get('navdata').get('appliances').get('tabs')[0].get('columns') men_columns_list=res.json().get('navdata').get('men').get('tabs')[0].get('columns') women_columns_list=res.json().get('navdata').get('women').get('tabs')[0].get('columns') baby_kids_columns_list=res.json().get('navdata').get('baby-kids').get('tabs')[0].get('columns') home_kitchen_columns_list=res.json().get('navdata').get('home-kitchen').get('tabs')[0].get('columns') nav_columns_lists =appliances_columns_list+men_columns_list+women_columns_list+baby_kids_columns_list+home_kitchen_columns_list for nav_columns_list in nav_columns_lists: for title_url_type_dict in nav_columns_list: print(title_url_type_dict.get('url'))
#page参数控制 如:https://www.flipkart.com/womens-footwear/pr?sid=osp,iko&page=3
from requests_html import htmlsession session =htmlsession() res =session.get('https://www.flipkart.com/womens-footwear/pr?sid=osp,iko&page=3', verify=false) print(res.html.xpath('//*[@id="container"]/div/div[3]/div[2]/div[1]/div[2]/div/div/div/div/div/a[1]/@href')[4:])
如对本文有疑问,请在下面进行留言讨论,广大热心网友会与你互动!! 点击进行留言回复
Python 实现将numpy中的nan和inf,nan替换成对应的均值
python爬虫把url链接编码成gbk2312格式过程解析
网友评论