selenium控制浏览器滚动条缓慢下拉到最底
1. ⽂章动态爬取的⼀个例⼦
import time
from selenium import webdriver
driver = webdriver.Chrome()
<("mp.weixin.qq/s/FCsJMGlWvwfR18YtLSLKtQ")
time.sleep(1)
# 执⾏这段代码，会获取到当前窗⼝总⾼度
js控制滚动条js = "return action=document.body.scrollHeight"
# 初始化现在滚动条所在⾼度为0
height = 0
# 当前窗⼝总⾼度
new_height = ute_script(js)
while height < new_height:
# 将滚动条调整⾄页⾯底部
for i in range(height, new_height, 100):
time.sleep(0.5)
height = new_height
time.sleep(2)
new_height = ute_script(js)
# window下保存⽂件要转码utf-8
with open(r'b.html', 'wb') as f:
f.write(driver.de('utf-8'))
driver.close()
⼆. 微博模拟登陆
1. 百度搜微博开放平台可满⾜爬取量不⼤的情况
2. 微博模拟登陆和下拉⿏标应对ajax加载
from selenium import webdriver
import time
browser = webdriver.Chrome()
<('www.weibo')
time.sleep(10)
browser.find_element_by_css_selector("#loginname").send_keys("1388057xxxx")
browser.find_element_by_css_selector(".info_list.password input[node-type='password']").send_keys("shiyan823")
browser.find_element_by_css_selector(".info_list.login_btn a[node-type='submitBtn']").click()
# ⿏标下拉
for i in range(3):
time.sleep(3)

版权声明：本站内容均来自互联网，仅供演示用，请勿用于商业和其他非法用途。如果侵犯了您的权益请与我们联系QQ:729038198，我们将在24小时内删除。