chrome.exe –remote-debugging-port=9222 –user-data-dir=”E:\data_info\selenium_data”

from selenium import webdriver
from selenium.webdriver.common.action_chains import ActionChains
import time
import json
import requests
import pymysql
from selenium.webdriver.common.keys import Keys
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.support.ui import WebDriverWait

config={
    "host":"10.50.3.116",
    "user":"crm",
    "password":"123456",
    "database":"t8t_tbt_spider_test"
}
db = pymysql.connect(**config)

def load_photo(url, name):
    '''给定图片链接，将图片以某个名称下载到本地'''
    # url = 'http://img14.360buyimg.com/n1/s450x450_jfs/t1/148801/37/12770/118749/5f9d71e4E39f1e893/533675187c108953.jpg'
    reponse = requests.get(url)
    # name = 'd:/photo.jpg'
    with open(name, 'wb') as ft:
        ft.write(reponse.content)

def drop_scroll(browser):
    '''将滑条从头滚动到底,以便让浏览器充分加载'''
    for x in range(1, 11, 2):
        # time.sleep(0.5)
        j = x/10
        js = 'document.documentElement.scrollTop = document.documentElement.scrollHeight * %f' % j
        browser.execute_script(js)

def switch_window(browser):
    '''将browser的指令移到新打开的小窗口处'''
    # time.sleep(0.5) # 如果移转失败，请增大这个时间
    windows = browser.window_handles
    browser.switch_to.window(windows[-1])

def switch_window_back(browser):
    '''将browser的指令移回旧的小窗口'''
    windows = browser.window_handles
    browser.switch_to.window(windows[0])


# 构造网址
u_id= input('请输入https://www.zhihu.com/people/{u_id}中的u_id')
url = f'https://www.zhihu.com/people/{u_id}'
page = int(input("要遍历的页数(从第一页开始)"))

# 打开知乎
chrome_options = Options()
chrome_options.add_experimental_option("debuggerAddress", "127.0.0.1:9222")  #  前面设置的端口号
browser = webdriver.Chrome(options=chrome_options)

# browser.set_window_size(900, 500) # 设置窗口大小
# browser.set_window_position(300, 200) # 设置浏览器的位置
browser.get(url)
btn=browser.find_element("xpath","//button[@aria-label='关闭']")
browser.execute_script("arguments[0].click();", btn)
time.sleep(5)

# 遍历页面中每篇回答
count = 1 # 回答的编号
for page_id in range(45,page+1):
    # 翻页
    #print("Page:%d" %page_id)
    #url = f'https://www.zhihu.com/people/{u_id}/answers/by_votes/?page={page_id}'
    url = f'https://www.zhihu.com/org/{u_id}/answers?page={page_id}'
    browser.get(url)
    time.sleep(2)
    btn = browser.find_element("xpath","//button[@aria-label='关闭']")
    browser.execute_script("arguments[0].click();", btn)
    time.sleep(5)
    switch_window_back(browser)  # 将browser的指令移回到新标签页
    drop_scroll(browser)     #滑条拖到底，让加载完全
    answers = browser.find_elements("xpath","//div[@class='ContentItem AnswerItem']")  # 获取所有回答
    for answer in answers:
        url = answer.find_element("xpath",".//a[@data-za-detail-view-element_name='Title']").get_attribute('href')
        title = answer.find_element("xpath",".//a[@data-za-detail-view-element_name='Title']").text
        print(count\
              ,answer.find_element("xpath",".//a[@data-za-detail-view-element_name='Title']").get_attribute('href')\
              , answer.find_element("xpath",".//a[@data-za-detail-view-element_name='Title']").text
              , sep=',')
        #print(count)
        nimeitime = time.time()
        cursor = db.cursor()
        sql="insert into sp_zhihu_list (title,url,source_from,name,create_time) values ('"+title+"','"+url+"',4,'装小蜜监理王志峰','"+str(nimeitime)+"')"
        cursor.execute(sql)  # 执行 sql
        db.commit()
        cursor.close()
        count=count+1