# 所有文字保存为txt
# 有图片的自动下载，没有图片的就不下载import os
import time
from selenium import webdriver
from bs4 import BeautifulSoup
import urllib.request
import randomclass Lofter:def __init__(self):self.pageleap = int(input('要从第几页开始下载'))self.articleleap = int(input('要从第{}页的第几篇开始下载'.format(self.pageleap)))self.username = input('请输入手机号')self.password = input('请输入密码')self.savepathf = input('请输入保存地址')def get_driver(self):exe_path = os.path.join(os.path.split(__file__)[0], 'chromedriver.exe')chrome_options = webdriver.ChromeOptions()chrome_options.add_argument('--headless')  # 增加无界面选项chrome_options.add_argument('--disable-gpu')  # 如果不加这个选项，有时定位会出现问题self.driver = webdriver.Chrome(executable_path=exe_path, options=chrome_options)  # 声明浏览器url = 'http://www.lofter.com/'self.driver.get(url)  # 打开浏览器预设网址self.driver.implicitly_wait(30)  # 隐式等待time.sleep(2)def log_in_by_tel(self):ele_login = self.driver.find_element_by_xpath('/html/body/div[1]/div[4]/div/div[2]/div[2]/div[2]/div/div[5]/div/ul/li[1]/a')ele_login.click()time.sleep(2)ele_tel = self.driver.find_element_by_xpath('/html/body/div[1]/div[4]/div/div[2]/div[2]/div[2]/div/div[4]/div[1]/input')ele_tel.send_keys(self.username)time.sleep(3)ele_pin = self.driver.find_element_by_xpath('/html/body/div[1]/div[4]/div/div[2]/div[2]/div[2]/div/div[4]/div[2]/input')ele_pin.send_keys(self.password)time.sleep(3)ele_yes = self.driver.find_element_by_xpath('/html/body/div[1]/div[4]/div/div[2]/div[2]/div[2]/div/div[4]/div[4]/span[1]/input')ele_yes.click()time.sleep(2)ele_log = self.driver.find_element_by_xpath('/html/body/div[1]/div[4]/div/div[2]/div[2]/div[2]/div/div[4]/div[3]')ele_log.click()self.driver.implicitly_wait(30)time.sleep(2)def xihuan(self):ele_xihuan = self.driver.find_element_by_xpath('/html/body/div[3]/div/div[2]/div[1]/div/div[2]/ul/li[4]/a/span[2]')ele_xihuan.click()time.sleep(5)windows = self.driver.window_handles  # 获取打开的多个窗口句柄self.driver.switch_to.window(windows[-1])  # 切换到当前最新打开的窗口self.driver.implicitly_wait(30)time.sleep(2)for i in range(1, 5):self.downward()def downward(self):self.driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")time.sleep(2)def tiaozhuan(self):for i in range(1, self.pageleap):ele_next_page = self.driver.find_element_by_css_selector('[class="next iblock"]')ele_next_page.click()time.sleep(3)windows = self.driver.window_handles  # 获取打开的多个窗口句柄self.driver.switch_to.window(windows[0])time.sleep(2)def findarticle(self, article):ele_page = self.driver.find_element_by_xpath('/html/body/div[3]/div/div[1]/div[{}]/div[3]/div/div[1]/a'.format(article + 4))ele_page.click()self.driver.implicitly_wait(30)windows = self.driver.window_handles  # 获取打开的多个窗口句柄self.driver.switch_to.window(windows[-1])  # 切换到当前最新打开的窗口self.driver.implicitly_wait(30)html = BeautifulSoup(self.driver.page_source, 'html.parser')title = html.title.get_text()return html, titledef downloadtext(self, page, article, html, title):try:text = html.find_all(class_='text')[1].get_text()except:try:text = html.find_all(class_='text')[0].get_text()except:text = ''try:txtcont = html.find_all(class_='txtcont')[0].get_text()except:txtcont = ''content = title + '\n' * 2 + text + '\n' * 2 + txtconttitle = title.replace("*", " ").replace("？", " ").replace("|", " ")title = title.replace("<", " ").replace(">", " ").replace(":", " ")title = title.replace("/", " ")try:savepath = self.savepathf + '{}_{} {}.txt'.format(page, article, title)with open(savepath, 'w', encoding='utf-8') as fb:fb.write(content)except:savepath = self.savepathf + '{}_{}.txt'.format(page, article)with open(savepath, 'w', encoding='utf-8') as fb:fb.write(content)time.sleep(2)def downloadpic(self, page, article, html, title):allpic = html.find_all(class_="img")allpiclen = len(allpic)for pic in range(1, allpiclen + 1):url = allpic[pic - 1].a.img['src']suff = os.path.splitext(url)[1].split('?')[0]title = title.replace("*", " ").replace("？", " ").replace("|", " ")title = title.replace("<", " ").replace(">", " ").replace(":", " ")title = title.replace("/", " ")try:picpath = self.savepathf + '{}_{} {}_{}{}'.format(page, article, title, pic, suff)time.sleep(random.randint(1, 3))urllib.request.urlretrieve(url, picpath)except:try:picpath = self.savepathf + '{}_{}_{}{}'.format(page, article, pic, suff)time.sleep(random.randint(1, 3))urllib.request.urlretrieve(url, picpath)except:print('{}_{}_{}{}未能保存'.format(page, article, pic, suff))def closearticle(self):# 关闭self.driver.close()time.sleep(2)windows = self.driver.window_handles  # 获取打开的多个窗口句柄self.driver.switch_to.window(windows[0])def save(self, i, j):html, title = self.findarticle(j)self.downloadtext(i, j, html, title)try:self.downloadpic(i, j, html, title)except:passself.closearticle()def loop(self):# 页面大循环for i in range(self.pageleap, 40):if i == self.pageleap:# 单篇小循环for j in range(self.articleleap, 120):try:self.save(i, j)except:print('第{}页第{}篇完蛋 or 第{}页完'.format(i, j, i))break# 下一页try:ele_next_page = self.driver.find_element_by_css_selector('[class="next iblock"]')ele_next_page.click()time.sleep(3)except:print('完蛋 or 全部结束')breakelse:# 单篇小循环for j in range(1, 120):try:self.save(i, j)except:print('第{}页第{}篇完蛋 or 第{}页完'.format(i, j, i))break# 下一页try:ele_next_page = self.driver.find_element_by_css_selector('[class="next iblock"]')ele_next_page.click()time.sleep(3)except:print('完蛋 or 全部结束')breakdef main(self):self.get_driver()self.log_in_by_tel()self.xihuan()if self.pageleap > 1:self.tiaozhuan()self.loop()if __name__ == '__main__':lofter = Lofter()lofter.main()