pip install selenium

from selenium import webdriver
import time
import re
#全局變量
driver = webdriver.Chrome("C:\Program Files (x86)\Google\Chrome\Application\chromedriver.exe")

def loginWeibo(username, password):
  driver.get('https://passport.weibo.cn/signin/login')
  time.sleep(1)

  driver.find_element_by_id("loginName").send_keys("haishu_zheng@163.com")
  driver.find_element_by_id("loginPassword").send_keys("Weibo01061122")

  time.sleep(1)
  driver.find_element_by_id("loginAction").click()

  #driver.close()
  
def visitUserPage(userId):
  driver.get('http://weibo.cn/' + userId)

  print('********************')  
  print('用戶資料')
  
  # 1.用戶id
  print('用戶id:' + userId)
  
  # 2.用戶昵稱
  strName = driver.find_element_by_xpath("http://div[@class='ut']")
  strlist = strName.text.split(' ')
  nickname = strlist[0]
  print('昵稱:' + nickname)
  
  # 3.微博數、粉絲數、關注數
  strCnt = driver.find_element_by_xpath("http://div[@class='tip2']")
  pattern = r"\d+\.?\d*" # 匹配數字，包含整數和小數
  cntArr = re.findall(pattern, strCnt.text)
  print(strCnt.text)
  print("微博數：" + str(cntArr[0]))
  print("關注數：" + str(cntArr[1]))
  print("粉絲數：" + str(cntArr[2]))
  
  print('\n********************')
  # 4.將用戶信息寫到文件里
  with open("weibo.txt", "w", encoding = "gb18030") as file:
    file.write("用戶ID：" + userId + '\r\n')
    file.write("昵稱：" + nickname + '\r\n')
    file.write("微博數：" + str(cntArr[0]) + '\r\n')
    file.write("關注數：" + str(cntArr[1]) + '\r\n')
    file.write("粉絲數：" + str(cntArr[2]) + '\r\n')
    
  # 5.獲取微博內容
  # http://weibo.cn/ + userId + ? filter=0&page=1
  # filter為0表示全部，為1表示原創
  print("微博內容")
  
  pageList = driver.find_element_by_xpath("http://div[@class='pa']")
  print(pageList.text)
  pattern = r"\d+\d*"     # 匹配數字，只包含整數
  pageArr = re.findall(pattern, pageList.text)
  totalPages = pageArr[1]   # 總共有多少頁微博
  print(totalPages)
  
  pageNum = 1     # 第幾頁
  numInCurPage = 1      # 當前頁的第幾條微博內容
  contentPath = "http://div[@class='c'][{0}]"
  while(pageNum <= 3):  
  #while(pageNum <= int(totalPages)):
    contentUrl = "http://weibo.cn/" + userId + "?filter=0&page=" + str(pageNum)
    driver.get(contentUrl)
    content = driver.find_element_by_xpath(contentPath.format(numInCurPage)).text
    # print("\n" + content) # 微博內容，包含原創和轉發
    if "設置:皮膚.圖片.條數.隱私" not in content:
      numInCurPage += 1
      with open("weibo.txt", "a", encoding = "gb18030") as file:
        file.write("\r\n" + "\r\n" + content)  # 將微博內容逐條寫到weibo.txt中
    else:
      pageNum += 1            # 抓取新一頁的內容
      numInCurPage = 1          # 每一頁都是從第1條開始抓    
    
if __name__ == '__main__':
  username = 'haishu_zheng@163.com'  # 輸入微博賬號
  password = 'Weibo01061122'     # 輸入密碼
  loginWeibo(username, password)   # 要先登錄，否則抓取不了微博內容
  time.sleep(3)
  uid = 'xywyw'            # 尋醫問藥
  visitUserPage(uid)