Python 爬蟲實(shí)戰(zhàn)之爬淘寶商品并做數(shù)據(jù)分析

import csvimport osimport timeimport wordcloudfrom selenium import webdriverfrom selenium.webdriver.common.by import By

def tongji():    prices = []    with open('前十頁銷量和金額.csv', 'r', encoding='utf-8', newline='') as f:        fieldnames = ['價(jià)格', '銷量', '店鋪位置']        reader = csv.DictReader(f, fieldnames=fieldnames)        for index, i in enumerate(reader):            if index != 0:                price = float(i['價(jià)格'].replace('￥', ''))                prices.append(price)    DATAS = {'<10': 0, '10~30': 0, '30~50': 0,             '50~70': 0, '70~90': 0, '90~110': 0,             '110~130': 0, '130~150': 0, '150~170': 0, '170~200': 0, }    for price in prices:        if price < 10:            DATAS['<10'] += 1        elif 10 <= price < 30:            DATAS['10~30'] += 1        elif 30 <= price < 50:            DATAS['30~50'] += 1        elif 50 <= price < 70:            DATAS['50~70'] += 1        elif 70 <= price < 90:            DATAS['70~90'] += 1        elif 90 <= price < 110:            DATAS['90~110'] += 1        elif 110 <= price < 130:            DATAS['110~130'] += 1        elif 130 <= price < 150:            DATAS['130~150'] += 1        elif 150 <= price < 170:            DATAS['150~170'] += 1        elif 170 <= price < 200:            DATAS['170~200'] += 1
    for k, v in DATAS.items():        print(k, ':', v)

def get_the_top_10(url):    top_ten = []    # 獲取代理    ip = zhima1()[2][random.randint(0, 399)]    # 運(yùn)行quicker動(dòng)作（可以不用管）    os.system('"C:\Program Files\Quicker\QuickerStarter.exe" runaction:5e3abcd2-9271-47b6-8eaf-3e7c8f4935d8')    options = webdriver.ChromeOptions()    # 遠(yuǎn)程調(diào)試Chrome    options.add_experimental_option('debuggerAddress', '127.0.0.1:9222')    options.add_argument(f'--proxy-server={ip}')    driver = webdriver.Chrome(options=options)    # 隱式等待    driver.implicitly_wait(3)    # 打開網(wǎng)頁    driver.get(url)    # 點(diǎn)擊部分文字包含'銷量'的網(wǎng)頁元素    driver.find_element(By.PARTIAL_LINK_TEXT, '銷量').click()    time.sleep(1)    # 頁面滑動(dòng)到最下方    driver.execute_script('window.scrollTo(0,document.body.scrollHeight)')    time.sleep(1)    # 查找元素    element = driver.find_element(By.ID, 'mainsrp-itemlist').find_element(By.XPATH, './/div[@class="items"]')    items = element.find_elements(By.XPATH, './/div[@data-category="auctions"]')    for index, item in enumerate(items):        if index == 10:            break        # 查找元素        price = item.find_element(By.XPATH, './div[2]/div[1]/div[contains(@class,"price")]').text        paid_num_data = item.find_element(By.XPATH, './div[2]/div[1]/div[@class="deal-cnt"]').text        store_location = item.find_element(By.XPATH, './div[2]/div[3]/div[@class="location"]').text        store_href = item.find_element(By.XPATH, './div[2]/div[@class="row row-2 title"]/a').get_attribute(            'href').strip()        # 將數(shù)據(jù)添加到字典        top_ten.append(            {'價(jià)格': price,             '銷量': paid_num_data,             '店鋪位置': store_location,             '店鋪鏈接': store_href             })
    for i in top_ten:        print(i)

def get_top_10_comments(url):    with open('排名前十評(píng)價(jià).txt', 'w+', encoding='utf-8') as f:        pass    # ip = ipidea()[1]    os.system('"C:\Program Files\Quicker\QuickerStarter.exe" runaction:5e3abcd2-9271-47b6-8eaf-3e7c8f4935d8')    options = webdriver.ChromeOptions()    options.add_experimental_option('debuggerAddress', '127.0.0.1:9222')    # options.add_argument(f'--proxy-server={ip}')    driver = webdriver.Chrome(options=options)    driver.implicitly_wait(3)    driver.get(url)    driver.find_element(By.PARTIAL_LINK_TEXT, '銷量').click()    time.sleep(1)    element = driver.find_element(By.ID, 'mainsrp-itemlist').find_element(By.XPATH, './/div[@class="items"]')    items = element.find_elements(By.XPATH, './/div[@data-category="auctions"]')    original_handle = driver.current_window_handle    item_hrefs = []    # 先獲取前十的鏈接    for index, item in enumerate(items):        if index == 10:            break        item_hrefs.append(            item.find_element(By.XPATH, './/div[2]/div[@class="row row-2 title"]/a').get_attribute('href').strip())    # 爬取前十每個(gè)商品評(píng)價(jià)    for item_href in item_hrefs:        # 打開新標(biāo)簽        # item_        driver.execute_script(f'window.open("{item_href}")')        # 切換過去        handles = driver.window_handles        driver.switch_to.window(handles[-1])
        # 頁面向下滑動(dòng)一部分，直到讓評(píng)價(jià)那兩個(gè)字顯示出來        try:            driver.find_element(By.PARTIAL_LINK_TEXT, '評(píng)價(jià)').click()        except Exception as e1:            try:                x = driver.find_element(By.PARTIAL_LINK_TEXT, '評(píng)價(jià)').location_once_scrolled_into_view                driver.find_element(By.PARTIAL_LINK_TEXT, '評(píng)價(jià)').click()            except Exception as e2:                try:                    # 先向下滑動(dòng)100，放置評(píng)價(jià)2個(gè)字沒顯示在屏幕內(nèi)                    driver.execute_script('var q=document.documentElement.scrollTop=100')                    x = driver.find_element(By.PARTIAL_LINK_TEXT, '評(píng)價(jià)').location_once_scrolled_into_view                except Exception as e3:                    driver.find_element(By.XPATH, '/html/body/div[6]/div/div[3]/div[2]/div/div[2]/ul/li[2]/a').click()        time.sleep(1)        try:            trs = driver.find_elements(By.XPATH, '//div[@class="rate-grid"]/table/tbody/tr')            for index, tr in enumerate(trs):                if index == 0:                    comments = tr.find_element(By.XPATH, './td[1]/div[1]/div/div').text.strip()                else:                    try:                        comments = tr.find_element(By.XPATH,                                                   './td[1]/div[1]/div[@class="tm-rate-fulltxt"]').text.strip()                    except Exception as e:                        comments = tr.find_element(By.XPATH,                                                   './td[1]/div[1]/div[@class="tm-rate-content"]/div[@class="tm-rate-fulltxt"]').text.strip()                with open('排名前十評(píng)價(jià).txt', 'a+', encoding='utf-8') as f:                    f.write(comments + '\n')                    print(comments)        except Exception as e:            lis = driver.find_elements(By.XPATH, '//div[@class="J_KgRate_MainReviews"]/div[@class="tb-revbd"]/ul/li')            for li in lis:                comments = li.find_element(By.XPATH, './div[2]/div/div[1]').text.strip()                with open('排名前十評(píng)價(jià).txt', 'a+', encoding='utf-8') as f:                    f.write(comments + '\n')                    print(comments)

def get_top_10_comments_wordcloud():    file = '排名前十評(píng)價(jià).txt'    f = open(file, encoding='utf-8')    txt = f.read()    f.close()
    w = wordcloud.WordCloud(width=1000,                            height=700,                            background_color='white',                            font_path='msyh.ttc')    # 創(chuàng)建詞云對(duì)象，并設(shè)置生成圖片的屬性
    w.generate(txt)    name = file.replace('.txt', '')    w.to_file(name + '詞云.png')    os.startfile(name + '詞云.png')

def get_10_pages_datas():    with open('前十頁銷量和金額.csv', 'w+', encoding='utf-8', newline='') as f:        f.write('\ufeff')        fieldnames = ['價(jià)格', '銷量', '店鋪位置']        writer = csv.DictWriter(f, fieldnames=fieldnames)        writer.writeheader()    infos = []    options = webdriver.ChromeOptions()    options.add_experimental_option('debuggerAddress', '127.0.0.1:9222')    # options.add_argument(f'--proxy-server={ip}')    driver = webdriver.Chrome(options=options)    driver.implicitly_wait(3)    driver.get(url)    # driver.execute_script('window.scrollTo(0,document.body.scrollHeight)')    element = driver.find_element(By.ID, 'mainsrp-itemlist').find_element(By.XPATH, './/div[@class="items"]')    items = element.find_elements(By.XPATH, './/div[@data-category="auctions"]')    for index, item in enumerate(items):        price = item.find_element(By.XPATH, './div[2]/div[1]/div[contains(@class,"price")]').text        paid_num_data = item.find_element(By.XPATH, './div[2]/div[1]/div[@class="deal-cnt"]').text        store_location = item.find_element(By.XPATH, './div[2]/div[3]/div[@class="location"]').text        infos.append(            {'價(jià)格': price,             '銷量': paid_num_data,             '店鋪位置': store_location})    try:        driver.find_element(By.PARTIAL_LINK_TEXT, '下一').click()    except Exception as e:        driver.execute_script('window.scrollTo(0,document.body.scrollHeight)')        driver.find_element(By.PARTIAL_LINK_TEXT, '下一').click()    for i in range(9):        time.sleep(1)        driver.execute_script('window.scrollTo(0,document.body.scrollHeight)')        element = driver.find_element(By.ID, 'mainsrp-itemlist').find_element(By.XPATH, './/div[@class="items"]')        items = element.find_elements(By.XPATH, './/div[@data-category="auctions"]')        for index, item in enumerate(items):            try:                price = item.find_element(By.XPATH, './div[2]/div[1]/div[contains(@class,"price")]').text            except Exception:                time.sleep(1)                driver.execute_script('window.scrollTo(0,document.body.scrollHeight)')                price = item.find_element(By.XPATH, './div[2]/div[1]/div[contains(@class,"price")]').text            paid_num_data = item.find_element(By.XPATH, './div[2]/div[1]/div[@class="deal-cnt"]').text            store_location = item.find_element(By.XPATH, './div[2]/div[3]/div[@class="location"]').text            infos.append(                {'價(jià)格': price,                 '銷量': paid_num_data,                 '店鋪位置': store_location})        try:            driver.find_element(By.PARTIAL_LINK_TEXT, '下一').click()        except Exception as e:            driver.execute_script('window.scrollTo(0,document.body.scrollHeight)')            driver.find_element(By.PARTIAL_LINK_TEXT, '下一').click()        # 一頁結(jié)束        for info in infos:            print(info)        with open('前十頁銷量和金額.csv', 'a+', encoding='utf-8', newline='') as f:            fieldnames = ['價(jià)格', '銷量', '店鋪位置']            writer = csv.DictWriter(f, fieldnames=fieldnames)            for info in infos:                writer.writerow(info)

if __name__ == '__main__':    url = 'https://s.taobao.com/search?q=%E5%B0%8F%E9%B1%BC%E9%9B%B6%E9%A3%9F&imgfile=&commend=all&ssid=s5-e&search_type=item&sourceId=tb.index&spm=a21bo.21814703.201856-taobao-item.1&ie=utf8&initiative_id=tbindexz_20170306&bcoffset=4&ntoffset=4&p4ppushleft=2%2C48&s=0'    # get_10_pages_datas()    # tongji()    # get_the_top_10(url)    # get_top_10_comments(url)????get_top_10_comments_wordcloud()