第一周大作业58

总结，
1、感觉58网站还在改， 时间没有找到，但是浏览量一下搞定了。
2、字符串的处理，或者说空值的处理，感觉if else 还有些难度，
3、find_all 还是感觉很难，需要看文档吧

成果抓图

weekdazuoye.jpg

代码

#!C:\Python35\python.exe
# coding=utf-8

from bs4 import BeautifulSoup
import requests
import time
'''
url = 'http://zhuanzhuan.58.com/detail/764095267672850433z.shtml'
wb_data = requests.get(url)
soup = BeautifulSoup(wb_data.text,'lxml')

 #soup.find_all('body > div.content > div > div.box_left > div.info_lubotu.clearfix > div.info_massege.left > div.palce_li > span > i')

kk=soup.select('body > div.content > div > div.box_left > div.info_lubotu.clearfix > div.info_massege.left > div.palce_li > span > i')
vv=kk[0].text
print(kk)
print(vv)
'''
#soup.find_all nanduda

#print(soup) #date come



def get_links_from(who_sells):
    urls = []
    list_view = 'http://bj.58.com/pbdn/{}/pn2/'.format(str(who_sells))
    wb_data = requests.get(list_view)
    soup = BeautifulSoup(wb_data.text,'lxml')
    for link in soup.select('td.t a.t'):
    #for link in soup.select('td.t a.t'):
        # infolist > div.infocon > table > tbody > tr > td.t > a
        urls.append(link.get('href').split('?')[0])
        print(urls)
    return urls

def get_views_from(url):    #nan我还是要以后研究一下，这是什么，希望老师到时候能讲解
    id = url.split('/')[-1].strip('x.shtml')
    api = 'http://jst1.58.com/counter?infoid={}'.format(id)
    # 这个是找到了58的查询接口，不了解接口可以参照一下新浪微博接口的介绍
    js = requests.get(api)
    views = js.text.split('=')[-1]
    return views
    # print(views)

def get_item_info(who_sells=0):
    urls = get_links_from(who_sells)
    time.sleep(1)
    for url in urls:
        wb_data = requests.get(url)
        soup = BeautifulSoup(wb_data.text,'lxml')
        data = {
            'title':soup.select('title')[0].text.split('\r\n')[1].strip(),
            # 'price':soup.select('price')[0].text,
            'price': (str(soup.select('.price_now')[0]).split('<i>')[1]).split('<')[0],
            #body > div.content > div > div.box_left > div.info_lubotu.clearfix > div.info_massege.left > div.price_li > span > i
            'area' :soup.select('body > div.content > div > div.box_left > div.info_lubotu.clearfix > div.info_massege.left > div.palce_li > span > i')[0].text,
            'date' :soup.select('.look_time')[0].text,
           # 'area' :list(soup.select('body > div.content > div > div.box_left > div.info_lubotu.clearfix > div.info_massege.left > div.palce_li > span > i')[0].stripped_strings) if soup.find_all('span','区域：') else None,
            #'date' :soup.select('.look_time')[0].text,
            'cate' :'个人' if who_sells == 0 else '商家', #这具体是什么意思？
            # 'views':get_views_from(url)
            #'views' :soup.select('.look_time')[0].text
        }
        print(data)

# get_item_info(url)
# get_links_from(1)
get_item_info() #qidong