代码拉取完成,页面将自动刷新
同步操作将从 mirrors_wistbean/learn_python3_spider 强制同步,此操作会覆盖自 Fork 仓库以来所做的任何修改,且无法恢复!!!
确定后同步将在后台操作,完成时将刷新页面,请耐心等待。
# coding=utf-8
# 最新版的selenium(4.x.x)已经不支持PhantomJS。如要用PhantomJS,可用旧版本selenium。如pip install selenium==3.8.0。
from selenium import webdriver
from selenium.common.exceptions import TimeoutException
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from bs4 import BeautifulSoup
import xlwt
# browser = webdriver.PhantomJS()
browser = webdriver.Chrome()
WAIT = WebDriverWait(browser, 10)
browser.set_window_size(1400, 900)
book = xlwt.Workbook(encoding='utf-8', style_compression=0)
sheet = book.add_sheet('蔡徐坤篮球', cell_overwrite_ok=True)
sheet.write(0, 0, '名称')
sheet.write(0, 1, '地址')
sheet.write(0, 2, '描述')
sheet.write(0, 3, '观看次数')
sheet.write(0, 4, '弹幕数')
sheet.write(0, 5, '发布时间')
n = 1
def search():
try:
print('开始访问b站....')
browser.get("https://www.bilibili.com/")
# 被那个破登录遮住了
# index = WAIT.until(EC.element_to_be_clickable((By.CSS_SELECTOR, "#primary_menu > ul > li.home > a")))
# index.click()
input = WAIT.until(EC.presence_of_element_located((By.CSS_SELECTOR, "#nav_searchform > input")))
submit = WAIT.until(EC.element_to_be_clickable(
(By.XPATH, '/html/body/div[2]/div/div[1]/div[1]/div/div[2]/div/form/div/button')))
input.send_keys('蔡徐坤 篮球')
submit.click()
# 跳转到新的窗口
print('跳转到新窗口')
all_h = browser.window_handles
browser.switch_to.window(all_h[1])
get_source()
total = WAIT.until(EC.presence_of_element_located((By.CSS_SELECTOR,
"#all-list > div.flow-loader > div.page-wrap > div > ul > li.page-item.last > button")))
return int(total.text)
except TimeoutException:
return search()
def next_page(page_num):
try:
print('获取下一页数据')
next_btn = WAIT.until(EC.element_to_be_clickable((By.CSS_SELECTOR,
'#all-list > div.flow-loader > div.page-wrap > div > ul > li.page-item.next > button')))
next_btn.click()
WAIT.until(EC.text_to_be_present_in_element((By.CSS_SELECTOR,
'#all-list > div.flow-loader > div.page-wrap > div > ul > li.page-item.active > button'),
str(page_num)))
get_source()
except TimeoutException:
browser.refresh()
return next_page(page_num)
def save_to_excel(soup):
list = soup.find(class_='video-list clearfix').find_all(class_='video-item matrix')
for item in list:
item_title = item.find('a').get('title')
item_link = item.find('a').get('href')
item_dec = item.find(class_='des hide').text
item_view = item.find(class_='so-icon watch-num').text
item_biubiu = item.find(class_='so-icon hide').text
item_date = item.find(class_='so-icon time').text
print('爬取:' + item_title)
global n
sheet.write(n, 0, item_title)
sheet.write(n, 1, item_link)
sheet.write(n, 2, item_dec)
sheet.write(n, 3, item_view)
sheet.write(n, 4, item_biubiu)
sheet.write(n, 5, item_date)
n = n + 1
def get_source():
WAIT.until(EC.presence_of_element_located(
(By.CSS_SELECTOR, '#all-list > div.flow-loader > div.filter-wrap')))
html = browser.page_source
soup = BeautifulSoup(html, 'lxml')
print('到这')
save_to_excel(soup)
def main():
try:
total = search()
print(total)
for i in range(2, int(total + 1)):
next_page(i)
finally:
browser.close()
if __name__ == '__main__':
main()
book.save('蔡徐坤篮球.xlsx')
此处可能存在不合适展示的内容,页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容,可点击提交进行申诉,我们将尽快为您处理。