最近閑著在家無(wú)聊摇幻，就看看爬蟲的書籍颓芭，突然發(fā)現(xiàn)很有趣顷锰，就寫了許多代碼，爬取了許多的網(wǎng)站亡问，今天就分享爬取京東的源代碼官紫。

#京東商品信息爬蟲  
#爬取京東商品信息并保存到csv格式文件中  
#2017-7-23  
  
  
import os  
import requests  
import csv  
from bs4 import BeautifulSoup  
  
#獲取url請(qǐng)求  
def gethtml(kind,page):  
    '''''獲取url請(qǐng)求'''  
    pagenum = str(2 * page)  
    try:  
        r = requests.get('https://search.jd.com/Search?keyword=' + \  
        kind + '&enc=utf-8&page=' + pagenum)#鏈接url  
        r.raise_for_status()  
        r.encoding = r.apparent_encoding#轉(zhuǎn)碼  
        print('爬取第{}頁(yè)：'.format(page))  
        return r.text#返回html  
    except:  
        print('鏈接異常！Ｖ菖骸束世！')  
        return ''  
  
#獲取定位資源  
def findhtml(html,httplist):  
    """尋找資源"""  
    soup = BeautifulSoup(html,'lxml')  
    links = soup.find_all('div', class_='gl-i-wrap')#尋找'div'標(biāo)簽  
    for link in links:  
        ui = []  
        namediv = link.find('div', class_='p-name p-name-type-2')#尋找商品名稱和鏈接  
        title = namediv.a['title']  
        href = namediv.a['href']  
        ui.append(title)#名稱加入到ui中  
        pricediv = link.find('div', class_='p-price')#尋找商品價(jià)格  
        try:  
            price =  pricediv.strong['data-price']   
            ui.append(price)#價(jià)格加入到ui中  
        except:  
            ui.append('')  
        if 'https:' not in href:#添加鏈接  
            ui.append('https:' + href)  
        else:  
            ui.append(href)  
        aggressmentdiv = link.find('div', class_='p-commit')#尋找評(píng)論  
        number = aggressmentdiv.strong.contents[1].string  
        ui.append(number)#評(píng)論數(shù)添加到ui中  
        httplist.append(ui)  
        try:  
            if price:  
                print('{:^10s}:{:<}元'.format(title,price))  
            else:  
                print('{:^10s}'.format(title))  
        except:  
            print('{:^10s}'.format(title))  
  
  
#保存資源  
def savehtml(ul):  
    path = 'D:/數(shù)據(jù)/'  
    if not os.path.exists(path):  
        os.mkdir(path)#創(chuàng)建一個(gè)文件  
    with open(path + '京東商品信息爬蟲.csv','w+') as f:  
        writer = csv.writer(f)  
        writer.writerow(['商品','價(jià)格','鏈接','評(píng)價(jià)數(shù)'])  
        for u in range(len(ul)):  
            if ul[u]:  
                writer.writerow([ul[u][0],ul[u][1],ul[u][2],ul[u][3]])  
  
  
  
#程序主體  
if __name__ == '__main__':  
    goods = input('請(qǐng)輸入要搜索的物品：')  
    yeshu = int(input('請(qǐng)輸入要查詢到的頁(yè)數(shù):'))  
    ulist = []  
    for i in range(yeshu+1):  
        try:  
            if i != 0:  
                text = gethtml(goods,i)  
                findhtml(text,ulist)  
            savehtml(ulist)  
        except:  
            break