def download(cid): client = ZhihuClient() client.load_token('token.pk1') # 登陆 column = client.column(cid) images_dir = os.path.join(column.title, 'images') regex = re.compile(r"https://pic\d.zhimg.com/", re.IGNORECASE) if not os.path.exists(column.title): os.makedirs(column.title) if not os.path.exists(images_dir): os.makedirs(images_dir) for index, article in enumerate(column.articles): # 处理文章 article_f = dealArticle(article) # 下载图片 downloadImg(article_f['content'], images_dir) # 替换图片路径 article_f['content'] = re.sub(regex, './images/', article_f['content']) # 写入 with open(os.path.join(column.title, article_f['title']), 'w+') as f: f.write(article_f['content']) print('[%s] download %s success!' % (str(index), article.title))
from lxml import html import requests, time, zhihu_oauth start_time = time.time() # 初始时间戳 # ========================登录======================== from zhihu_oauth import ZhihuClient client = ZhihuClient() client.load_token('/Users/alicewish/我的坚果云/token.pkl') # ============专栏模块============ cid = 10000 column = client.column(cid) print('文章数', column.article_count) print('文章', column.articles) print('文章数', column.articles_count) print('作者', column.author) print('能否评论', column.comment_permission) print('描述', column.description) print('关注人数', column.follower_count) print('关注人', column.followers) print('问题ID', column.id) print('图像地址', column.image_url) print('标题', column.title) print('是否更新过', column.updated) print('更新时间', time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(column.updated_time))) # ================运行时间计时================ run_time = time.time() - start_time if run_time < 60: # 两位小数的秒
from lxml import html import requests, time, zhihu_oauth start_time = time.time() # 初始时间戳 # ========================登录======================== from zhihu_oauth import ZhihuClient client = ZhihuClient() client.load_token('/Users/alicewish/我的坚果云/token.pkl') # ============专栏模块============ cid = 10000 column = client.column(cid) print('文章数', column.article_count) print('文章', column.articles) print('文章数', column.articles_count) print('作者', column.author) print('能否评论', column.comment_permission) print('描述', column.description) print('关注人数', column.follower_count) print('关注人', column.followers) print('问题ID', column.id) print('图像地址', column.image_url) print('标题', column.title) print('是否更新过', column.updated) print('更新时间', time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(column.updated_time))) # ================运行时间计时================ run_time = time.time() - start_time