爬取京東某個商品銷量數據

import selenium
from selenium import webdriver
import time
from selenium.webdriver import ActionChains
from selenium.webdriver.common.by import By #按照什么方式查找，By.ID,By.CSS_SELECTOR
from selenium.webdriver.common.keys import Keys #鍵盤按鍵操作
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.wait import WebDriverWait #等待頁面加載某些元素

from selenium.webdriver.chrome.options import Options
chrome_options = Options()
chrome_options.add_argument('--disable-gpu') #谷歌文檔提到需要加上這個屬性來規避bug
chrome_options.add_argument('blink-settings=imagesEnabled=false') #不加載圖片, 可以提升速度
chrome_options.add_argument('--headless') #瀏覽器不提供可視化頁面. linux下如果系統如果無界面不加這條會啟動失敗


kw = "手機"

driver = webdriver.Chrome(r"D:\脫產三期視頻\爬蟲3\chromedriver.exe",options=chrome_options)

driver.get("https://jd.com")
# 隱式等待
driver.implicitly_wait(3)

# 獲取輸入框
kw_input = driver.find_element_by_id("key")

# 輸入關鍵字
kw_input.send_keys(kw)
# 模擬點擊回車
kw_input.send_keys(Keys.ENTER)

# 獲取所有包含商品詳細數據的li
items = driver.find_elements_by_class_name("gl-item")
# 要獲取的數據 價格 商品鏈接 商品標題 評論數量


wait = WebDriverWait(driver, 10,0.5)

products = []
for i in  range(1):

    for item in items:
        wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '.p-img a')))

        url = item.find_element_by_css_selector(".p-img a").get_attribute("href")
        # print(url)

        wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '.p-price i')))
        price = item.find_element_by_css_selector(".p-price i").text
        # print(price)

        wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '.p-name a')))
        title = item.find_element_by_css_selector(".p-name a").text
        # print(title)

        wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '.p-commit strong a')))
        commit = item.find_element_by_css_selector(".p-commit strong a").text
        # print(commit)

        products.append({"url":url,"price":price,"title":title,"commit":commit})
    # 在這里點擊下一頁
    # print("開始下一頁")
    # next_tag = driver.find_element_by_link_text(">")
    # next_tag.click()
    # 等待2秒開始獲取下一頁
    # driver.implicitly_wait(50) #由於網頁是局部刷新 所以隱式等待無效
    # 獲取所有包含商品詳細數據的li
    # wait.until(EC.presence_of_element_located((By.CLASS_NAME, 'gl-item')))
    # time.sleep(3)
    # items = driver.find_elements_by_class_name("gl-item")


print([i["commit"] for i in products])

for i in products:
    commit = i["commit"]
    commit = commit.strip("+")
    if "萬" in commit:
        commit = commit.strip("萬")
        commit = float(commit) * 10000
    else:
        commit = float(commit)
    i["commit"] = commit

res = sorted(products,key= lambda d:d["commit"])
# print([i["commit"] for i in res])

print("恭喜銷量冠軍:",res[-1])