python爬虫存入excel却只重复第一行信息

Question

请问各位，python爬取网页信息的时候，print出来的都是对的，但是存入excel却全都是重复的第一行信息是怎么回事啊

driver = webdriver.Chrome()

driver.execute_cdp_cmd("Page.addScriptToEvaluateOnNewDocument",{
  "source": """
    Object.defineProperty(navigator, 'webdriver', {
      get: () => undefined
    })
  """
})

driver.get('https://kns.cnki.net/kns8/defaultresult/index')
time.sleep(1)
driver.find_element(By.ID,"txt_search").send_keys('福建妇女')   # .send_keys()  向搜索框中输入内容
driver.find_element(By.CLASS_NAME,"search-btn").click()       # .click() 代表点击动作
time.sleep(1)
datalist = []
# html = driver.page_source
# print(html)
while True:

    trs = driver.find_elements(By.XPATH,"//table[@class='result-table-list']/tbody/tr")
    for tr in trs:

        # 序号
        order = tr.find_element(By.XPATH,"./td[@class='seq']").text
        print(order)
        datalist.append(order)
        # 题目
        title = tr.find_element(By.XPATH,"./td[@class='name']").text
        print(title)
        datalist.append(title)
        # 论文链接
        href = tr.find_element(By.XPATH,"./td[@class='name']/a").get_attribute('href')
        print(href)
        datalist.append(href)
        # 作者

        author = tr.find_element(By.XPATH,"./td[@class='author']").text
        print(author)
        datalist.append(author)


        # 来源
        source = tr.find_element(By.XPATH,"./td[@class='source']").text
        print(source)
        datalist.append(source)
        # 发表时间
        pubtime = tr.find_element(By.XPATH,"./td[@class='date']").text
        print(pubtime)
        datalist.append(pubtime)
        # 发表类别
        category = tr.find_element(By.XPATH,"./td[@class='data']").text
        print(category)
        datalist.append(category)



    # 下一页
    try:
        next = driver.find_element(By.ID,"PageNext").click()
        time.sleep(2)
        html = driver.page_source
        print(html)
    except:
        print("没有下一页了")
        break

driver.quit()


print("saving")
workbook = xlwt.Workbook(encoding="utf-8")
worksheet = workbook.add_sheet('sheet1',cell_overwrite_ok=True)
col = ("序号","题目","链接","作者","来源","发表时间","类别")
for i in range(0,7):
    worksheet.write(0,i,col[i])
for i in range(0,180):
    # print("第%d条" %(i+1))
    datalist2 = datalist[i]
    for j in range(0,7):
        worksheet.write(i+1,j,datalist2[j])
   
workbook.save("zhiwang2.xls")

Answer 1

import time

import xlwt as xlwt
from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.common.by import By

# driver = webdriver.Chrome()
service = Service(r"D:\chromedriver.exe")
driver = webdriver.Chrome(service=service)
driver.execute_cdp_cmd("Page.addScriptToEvaluateOnNewDocument", {
    "source": """
    Object.defineProperty(navigator, 'webdriver', {
      get: () => undefined
    })
  """
})

driver.get('https://kns.cnki.net/kns8/defaultresult/index')
time.sleep(1)
driver.find_element(By.ID, "txt_search").send_keys('福建妇女')  # .send_keys()  向搜索框中输入内容
driver.find_element(By.CLASS_NAME, "search-btn").click()  # .click() 代表点击动作
time.sleep(1)
datalist = []
# html = driver.page_source
# print(html)
while True:
    trs = driver.find_elements(By.XPATH, "//table[@class='result-table-list']/tbody/tr")
    for tr in trs:
        # 序号
        order = tr.find_element(By.XPATH, "./td[@class='seq']").text
        print(order)
        # datalist.append(order)
        # 题目
        title = tr.find_element(By.XPATH, "./td[@class='name']").text
        print(title)
        # datalist.append(title)
        # 论文链接
        href = tr.find_element(By.XPATH, "./td[@class='name']/a").get_attribute('href')
        print(href)
        # datalist.append(href)
        # 作者
        author = tr.find_element(By.XPATH, "./td[@class='author']").text
        print(author)
        # datalist.append(author)
        # 来源
        source = tr.find_element(By.XPATH, "./td[@class='source']").text
        print(source)
        # datalist.append(source)
        # 发表时间
        pubtime = tr.find_element(By.XPATH, "./td[@class='date']").text
        print(pubtime)
        # datalist.append(pubtime)
        # 发表类别
        category = tr.find_element(By.XPATH, "./td[@class='data']").text
        print(category)
        # datalist.append(category)
        datalist.append([order, title, href, author, source, pubtime, category])
    # 下一页
    try:
        driver.find_element(By.ID, "PageNext").click()
        time.sleep(2)
        html = driver.page_source
        print(html)
    except:
        print("没有下一页了")
        break

driver.quit()

print("saving")
print(datalist)
workbook = xlwt.Workbook(encoding="utf-8")
worksheet = workbook.add_sheet('sheet1', cell_overwrite_ok=True)
col = ("序号", "题目", "链接", "作者", "来源", "发表时间", "类别")
for i in range(0, 7):
    worksheet.write(0, i, col[i])
for i in range(len(datalist)):
    datalist2 = datalist[i]
    for j in range(0, 7):
        worksheet.write(i + 1, j, datalist2[j])

workbook.save("zhiwang2.xls")