python学习之旅-第二周week2-2

week2-1作业
学习python的第二周 5.24号完成练习week2-1在爬取58手机号

Paste_Image.png

Paste_Image.png

Level1代码

from bs4 import BeautifulSoup
import requests
import time
import pymongo
client = pymongo.MongoClient('localhost',27017)
walden = client['58_message']
phones_message = walden['phones_message']
def get_phones_links(url):
    headers = {
        'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/46.0.2490.86 Safari/537.36',
        'Cookie':'ipcity=sh%7C%u4E0A%u6D77; userid360_xml=BE5F745CB21889493F55E2AB183C6316; time_create=1466562303322; f=n; f=n; ipcity=sh%7C%u4E0A%u6D77; userid360_xml=BE5F745CB21889493F55E2AB183C6316; time_create=1466562500982; bj58_id58s="ZGFzSVk5dkFyUDZQODU4OA=="; id58=c5/njVc0K1eW7SWOA1IbAg==; als=0; myfeet_tooltip=end; bdshare_firstime=1463552754347; 58home=sh; final_history=25359014999104%2C25390255065933%2C26044978248654%2C26044268155977%2C26013739776688; sessionid=83130bc4-3b8b-4861-b967-70d61d824c8e; bj58_new_session=0; bj58_init_refer=""; bj58_new_uv=5; 58tj_uuid=0f55bf86-b266-4866-aea3-3fed2ffe6ccf; new_session=0; new_uv=4; utm_source=; spm=; init_refer='
    }
    print(url)
    wb_date = requests.get(url)
    soup = BeautifulSoup(wb_date.text,'lxml')
    #标题
    titles = soup.select('strong.number')
    #连接
    links = soup.select('a.t')
    if len(titles)>0:
        for title, link in zip(titles, links):
            data = {
                '标题': title.get_text(),
                '连接': link.get('href')
            }
            phones_message.insert_one(data)
            print(data)
    else:
        pass



full_url = ['http://bj.58.com/shoujihao/pn{}/'.format(str(i)) for
            i in range(0, 200, 1)]
for link in full_url:
    time.sleep(3)#设置间隔时间 防止被屏蔽
    get_phones_links(link)

Level2代码

client = pymongo.MongoClient('localhost',27017)
walden = client['58_message']
#循环数据库 得到所有连接
phones_message_look = walden['phones_message_look']
def get_Db_Message():
    for message in phones_message.find():
        #if判断排除几个选好网的推荐
        if  'http://bj.58.com/shoujihao/' in message['连接']:
            print(message['连接'])
            get_phone_message(message['连接'])
            time.sleep(2)
    return
#获取详细页面内容
def get_phone_message(url):
    wb_data = requests.get(url)
    soup = BeautifulSoup(wb_data.text,'lxml')
    titles = soup.select('#main > div.col.detailPrimary.mb15 > div.col_sub.mainTitle > h1')#标题
    prices = soup.select('#main > div.col.detailPrimary.mb15 > div.col_sub.sumary > ul > li:nth-of-type(1) > div.su_con > span')#价格
    sellers = soup.select('#divContacter1 > ul > ul > li > a')#卖家姓名
    tels = soup.select('#t_phone')#联系方式
    areas = soup.select('div.su_con > a')  # 区域
    if(len(areas)==2):
        area = areas[0].get_text()+'-'+areas[1].get_text()
    elif(len(areas)==1):
        area = areas[0].get_text()
    else:
        area= 'None'
    for title,price,seller,tel in zip(titles,prices,sellers,tels):
        data = {
            '标题':((title.get_text().replace('\t','')).replace('\n','')).replace(' ','').strip(),#去除样式里\t \n 连续空格等不需要的样式
            '价格':price.get_text().strip(),
            '卖家姓名':seller.get_text().strip(),
            '联系电话':tel.get_text().strip(),
            '区域':area
        }
        print(data)
        phones_message_look.insert_one(data)
    return
get_Db_Message()

MongoDb数据库

Paste_Image.png

Paste_Image.png

总结:
-.通过本次学习练习，从58同城爬取手机号连接信息以及卖家信息3000余条
-.难点,在本次爬取卖家信息时，QQ信息为图片，但是根据观察应该是根据一个32位的加密字符串有关系，但是技术有限，没能爬去下QQ信息