下面整个流程无需登录
下载Google驱动CNPM Binaries Mirrorhttps://registry.npmmirror.com/binary.html?path=chromedriver/
放在程序运行的目录下即可, 注意要配上下边那句代码使用
driver = webdriver.Chrome(executable_path="./chromedriver")
先把直播页面下拉到底, 从而显示全部的直播信息
# 窗口下滑 scrollTop 页面的滑动条顶部
i = 1
while i <= 2800:
driver.execute_script('window.scrollTo({},{})'.format(i, i + 200))
i = i + 200
# time.sleep(1)
print(i)
else:
print('触底......')
# time.sleep(3)
# 查询
div_list = driver.find_elements_by_class_name('index_3Uym8ODI')
上面那行代码得到了所有class='index_3Uym8ODI'的标签
# 房间图片
room_img = div.find_element_by_xpath('.//div[@class="Item_2n7ef9LN"]').get_attribute('style')
.//div[@class="Item_2n7ef9LN"] 指的是从当前节点开始, 找到class="Item_2n7ef9LN"的div
图片在style里面, .get_attribute("style")即可拿到
其他同理可得
完整代码如下
from selenium import webdriver
import time, csv
driver = webdriver.Chrome(executable_path="./chromedriver")
driver.get('https://live.bilibili.com/p/eden/area-tags?areaId=0&parentAreaId=1')
room_list = []
# 窗口下滑 scrollTop 页面的滑动条顶部
i = 1
while i <= 2800:
driver.execute_script('window.scrollTo({},{})'.format(i, i + 200))
i = i + 200
# time.sleep(1)
print(i)
else:
print('触底......')
# time.sleep(3)
# 查询
div_list = driver.find_elements_by_class_name('index_3Uym8ODI')
for div in div_list:
try:
# 房间图片
room_img = div.find_element_by_xpath('.//div[@class="Item_2n7ef9LN"]').get_attribute('style')
# 房间标题
room_title = div.find_element_by_xpath('.//div[@class="Item_2GEmdhg6"]').text
# 房间类型
room_type = div.find_element_by_xpath('.//div[@class="Item_SI0N7ecx"]').text
# 房间名称
room_name = div.find_element_by_xpath('.//div[@class="Item_QAOnosoB"]').text
# 房间热度
room_hot = div.find_element_by_xpath('.//div[@class="Item_3Iz_3buh"]').text
room_list.append([room_name, room_type, room_hot, room_title, room_img])
except:
print('该房间无信息')
continue
else:
print(len(room_list))
file = open('./小破站主播房间信息{}.csv'.format(time.time()), 'w', encoding='utf-8') # 本地时间的时间戳格式
file_csv = csv.writer(file)
file_csv.writerow(['名称', '类型', '热度', '标题', '图片'])
file_csv.writerows(room_list)
file.flush()
file.close()
特别鸣谢: @故里17