def main(url): # 获取首页html内容 soup = http.get_html(url) # 提取分页之后的总页数 totalPage = http.get_total_page(soup) # 从页面中提取需要的数据 get_xiaohua_html(url,totalPage)
def get_xiaohua_html(url,page): for i in range(1,page+1): url2 = url + "/page/" + str(i) soup = http.get_html(url2) get_xiaohua(soup)
def main(url): soup = http.get_html(url) totalPage = http.get_total_page(soup) get_xiaohua_html(url,totalPage)