Python 爬虫学习2

任务：爬取租房网站信息，300个房源信息（详情页中的价格、位置、户主名字、性别等）

注意：超链接的获取、性别获取

from bs4 import BeautifulSoupimport requests, timepage_link = [] # <- 每个详情页的链接都存在这里，解析详情的时候就遍历这个列表然后访问就好啦~def get_page_link(page_number):#获取每一页中的详情页的链接    for each_number in range(1,page_number): # 每页24个链接,这里输入的是页码        full_url = 'http://bj.xiaozhu.com/search-duanzufang-p{}-0/'.format(each_number)        wb_data = requests.get(full_url)        soup = BeautifulSoup(wb_data.text,'lxml')        for link in soup.select('a.resule_img_a'): # 找到这个 class 样为resule_img_a 的 a 标签即可            page_link.append(link.get('href'))#只需要取出超链接添加到page_link中def PRint_gender(class_name):    if class_name == 'member_ico1':        return '女'    if class_name == 'member_ico':        return '男'url = 'http://bj.xiaozhu.com/fangzi/1508951935.html'def get_attractions(url, count):#获取每一个详情页的具体信息    wb_data = requests.get(url)    soup = BeautifulSoup(wb_data.text, 'lxml')    title = soup.select('div.wrap.clearfix.con_bg > div.con_l > div.pho_info > h4 > em')    address = soup.select(' div.wrap.clearfix.con_bg > div.con_l > div.pho_info > p > span')    price = soup.select(' div.day_l > span')    picture = soup.select('#curBigImage')    host_name = soup.select('#floatRightBox > div.js_box.clearfix > div.w_240 > h6 > a')    host_gender = soup.select('#floatRightBox > div.js_box.clearfix > div.member_pic > div')    for ti, add, pri, pic, name, gender in zip(title, address , price, picture, host_name, host_gender):#创建数据结构        data = {            'ti': ti.get_text(),            'add': add.get_text(strip=True), #strip去除前后空白，也可以使用.stripped_strings            'pri': pri.get_text(),            'pic': pic.get('src'),            'name': name.get_text(),            'gender':print_gender(gender.get('class')[0])        }    data['count']=count #增加计数功能    print(data)    get_page_link(13)   #爬取13页for i in range(1, 301): #爬取300条    # time.sleep(2)    get_attractions(page_link[i], i)