def run(self, cfg: dict):
if cfg['all']:
try:
dc = get_data_client(cfg)
except Exception:
sys.stderr.write(
"ERROR: invalid geektime account or password\n"
"Use '{} login --help' for help.\n".format(
sys.argv[0].split(os.path.sep)[-1]))
return
data = dc.get_course_list()
cid_list = []
for c in data['1']['list']:
if c['had_sub']:
cid_list.append(c['id'])
else:
course_ids = cfg['course_ids']
cid_list = course_ids.split(',')
for cid in cid_list:
args = cfg.copy()
args['course_id'] = int(cid)
super().run(args)
def run(self, cfg: dict):
cid_list = []
if cfg['all']:
try:
dc = get_data_client(cfg)
except:
sys.stderr.write(
"ERROR: invalid geektime account or password\n"
"Use '{} login --help' for help.\n".format(
sys.argv[0].split(os.path.sep)[-1]))
return
data = dc.get_course_list()
for c in data['1']['list'] + data['2']['list']:
if c['had_sub'] and (c['update_frequency'] == '全集'
or c['is_finish']):
cid_list.append(c['id'])
else:
course_ids = cfg['course_ids']
cid_list.extend(course_ids.split(','))
for cid in cid_list:
args = cfg.copy()
args['course_id'] = int(cid)
super().run(args)
sys.stderr.write('\n')
def run(self, cfg: dict):
try:
dc = get_data_client(cfg)
except:
sys.stderr.write("ERROR: invalid geektime account or password\n"
"Use '%s login --help' for help.\n" % sys.argv[0].split(os.path.sep)[-1])
return
data = dc.get_course_list()
result_str = ''
for i in ['1', '2', '3', '4']:
columns = data[i]['list']
result_str += {'1': '专栏', '2': '微课', '3': '视频', '4': '其他'}[i] + '\n'
result_str += "\t{:<12}{}\t{}\t{:<10}\n".format('课程ID', '已订阅', '已完结', '课程标题')
for c in columns:
result_str += "\t{:<15}{}\t{}\t{:<10}\n".format(
str(c['id']),
'是' if c['had_sub'] else '否',
'是' if c['is_finish'] else '否',
c['column_title'],
)
sys.stdout.write(result_str)
def run(self, cfg: dict):
course_id = cfg['course_id']
if not course_id:
sys.stderr.write("ERROR: couldn't find the target course id\n")
return
out_dir = os.path.join(cfg['output_folder'], 'mp3')
if not os.path.isdir(out_dir):
try:
os.makedirs(out_dir)
except OSError:
sys.stderr.write(
"ERROR: couldn't create the output folder {}\n".format(
out_dir))
return
url_only = cfg['url_only']
try:
dc = get_data_client(cfg)
except:
sys.stderr.write("ERROR: invalid geektime account or password\n"
"Use '%s <command> login --help' for help.\n" %
sys.argv[0].split(os.path.sep)[-1])
return
course_data = dc.get_course_intro(course_id)
if int(course_data['column_type']) != 1:
raise Exception('该课程不提供音频:%s' % course_data['column_title'])
out_dir = os.path.join(out_dir, course_data['column_title'])
if not os.path.isdir(out_dir):
os.makedirs(out_dir)
data = dc.get_course_content(course_id)
if url_only:
title = maker.format_file_name(course_data['column_title'])
with open(os.path.join(out_dir, '%s.mp3.txt' % title), 'w') as f:
# TODO alignment
f.write('\n'.join([
"{}:\t\t{}".format(
maker.format_file_name(post['article_title']),
post['audio_download_url']) for post in data
]))
sys.stdout.write('download {} mp3 url done\n'.format(title))
return
dl = Downloader()
for post in data:
file_name = maker.format_file_name(post['article_title']) + '.mp3'
if os.path.isfile(os.path.join(out_dir, file_name)):
sys.stdout.write(file_name + ' exists\n')
continue
if post['audio_download_url']:
dl.run(post['audio_download_url'],
out_file=file_name,
out_dir=out_dir)
sys.stdout.write('download mp3 {} done: \n'.format(file_name))
def run(self, cfg: dict):
try:
dc = get_data_client(cfg)
except Exception:
sys.stderr.write(
"ERROR: invalid geektime account or password\n"
"Use '{} login --help' for help.\n".format(
sys.argv[0].split(os.path.sep)[-1]))
return
data = dc.get_course_list()
result_str = ''
for i in ['1', '2', '3', '4']:
columns = data[i]['list']
result_str += _course_map[i] + '\n'
result_str += "\t{:<12}{}\t{}\t{:<10}\n".format(
'课程ID', '已订阅', '已完结', '课程标题')
for c in columns:
is_finished = c['update_frequency'] == '全集' or c['is_finish']
result_str += "\t{:<15}{}\t{}\t{:<10}\n".format(
str(c['id']),
'是' if c['had_sub'] else '否',
'是' if is_finished else '否',
c['column_title'],
)
sys.stdout.write(result_str)
def get_data_client(cfg: dict) -> DataClient:
try:
dc = get_data_client(cfg)
return dc
except Exception:
raise ValueError("invalid geektime account or password\n"
"Use '{} login --help' for help.\n".format(
sys.argv[0].split(os.path.sep)[-1]))
def run(self, cfg: dict) -> None:
# from ipdb import set_trace;set_trace()
course_id = cfg['course_id']
if not course_id:
sys.stderr.write("ERROR: couldn't find the target course id\n")
return
out_dir = os.path.join(cfg['output_folder'], 'ebook')
if not os.path.isdir(out_dir):
try:
os.makedirs(out_dir)
except OSError:
sys.stderr.write("ERROR: couldn't create the output folder {}\n".format(out_dir))
return
try:
dc = get_data_client(cfg)
except:
sys.stderr.write("ERROR: invalid geektime account or password\n"
"Use '%s <command> login --help' for help.\n" % sys.argv[0].split(os.path.sep)[-1])
return
course_data = dc.get_course_intro(course_id, force=True)
if int(course_data['column_type']) not in (1, 2):
sys.stderr.write("ERROR: 该课程不提供文本:%s" % course_data['column_title'])
return
# data
data = dc.get_course_content(course_id, force=cfg['force'])
if cfg['enable_comments']:
for post in data:
post['article_content'] += self._render_comment_html(post['comments'], cfg['comments_count'])
# source file
course_data['column_title'] = maker.format_file_name(course_data['column_title'])
self._render_column_source_files(course_data, data, out_dir, force=cfg['force'])
# ebook
if not cfg['source_only']:
if course_data['update_frequency'] == '全集' and os.path.isfile(os.path.join(out_dir, self._title(course_data)) + '.mobi'):
sys.stdout.write("{} exists\n".format(self._title(course_data)))
else:
make_mobi(source_dir=os.path.join(out_dir, course_data['column_title']), output_dir=out_dir)
# push to kindle
if cfg['push'] and not cfg['source_only']:
fn = os.path.join(out_dir, "{}.mobi".format(self._title(course_data)))
try:
send_to_kindle(fn, cfg)
sys.stdout.write("push to kindle done\n")
except Exception as e:
sys.stderr.write("ERROR: push to kindle failed, e={}\n".format(e))
def run(self, cfg: dict):
course_id = cfg['course_id']
if not course_id:
sys.stderr.write("ERROR: couldn't find the target course id\n")
return
out_dir = os.path.join(cfg['output_folder'], 'mp4')
out_dir = os.path.expanduser(out_dir)
if not os.path.isdir(out_dir):
try:
os.makedirs(out_dir)
except OSError:
sys.stderr.write(
"ERROR: couldn't create the output folder {}\n".format(
out_dir))
return
url_only = cfg['url_only']
hd_only = cfg['hd_only']
workers = cfg['workers']
try:
dc = get_data_client(cfg)
except:
sys.stderr.write("ERROR: invalid geektime account or password\n"
"Use '%s login --help' for help.\n" %
sys.argv[0].split(os.path.sep)[-1])
return
course_data = dc.get_course_intro(course_id)
if int(course_data['column_type']) != 3:
raise Exception('该课程不是视频课程:%s' % course_data['column_title'])
out_dir = os.path.join(out_dir, course_data['column_title'])
if not os.path.isdir(out_dir):
os.makedirs(out_dir)
sys.stdout.write('doing ......\n')
data = dc.get_course_content(course_id)
if url_only:
title = EbookRender.format_file_name(course_data['column_title'])
with open(os.path.join(out_dir, '%s.mp4.txt' % title), 'w') as f:
f.write('\n'.join([
"{}:\n{}\n{}\n\n".format(
EbookRender.format_file_name(post['article_title']),
post['video_media_map'].get('hd', {}).get('url'),
post['video_media_map'].get('sd', {}).get('url'))
for post in data
]))
sys.stdout.write('download {} mp4 url done\n'.format(title))
return
dl = Downloader()
p = Pool(workers)
start = time.time()
for post in data:
file_name = EbookRender.format_file_name(
post['article_title']) + ('.hd' if hd_only else '.sd')
if os.path.isfile(os.path.join(out_dir, file_name) + '.ts'):
sys.stdout.write(file_name + ' exists\n')
continue
if hd_only: # some post has sd mp4 only
url = post['video_media_map'].get(
'hd', {}).get('url') or post['video_media'].get(
'sd', {}).get('url')
else:
url = post['video_media_map'].get('sd', {}).get('url')
p.apply_async(dl.run, (url, out_dir, file_name))
p.close()
p.join()
sys.stdout.write('download {} done, cost {}s\n'.format(
course_data['column_title'], int(time.time() - start)))
def run(self, cfg: dict) -> None:
course_id = cfg['course_id']
if not course_id:
sys.stderr.write("ERROR: couldn't find the target course id\n")
return
out_dir = os.path.join(cfg['output_folder'], 'ebook')
out_dir = os.path.expanduser(out_dir)
if not os.path.isdir(out_dir):
try:
os.makedirs(out_dir)
except OSError:
sys.stderr.write(
"ERROR: couldn't create the output folder {}\n".format(
out_dir))
return
try:
dc = get_data_client(cfg)
except Exception:
sys.stderr.write("ERROR: invalid geektime account or password\n"
"Use '{} login --help' for help.\n".format(
sys.argv[0].split(os.path.sep)[-1]))
return
course_data = dc.get_course_intro(course_id, force=True)
if int(course_data['column_type']) not in (1, 2):
sys.stderr.write("ERROR: 该课程不提供文本:{}".format(
course_data['column_title']))
return
# data
sys.stdout.write('doing ......\n')
data = dc.get_course_content(course_id, force=cfg['force'])
if cfg['enable_comments']:
for post in data:
post['article_content'] += self._render_comment_html(
post['comments'], cfg['comments_count'])
# source file
course_data['column_title'] = Render.format_file_name(
course_data['column_title'])
self._render_source_files(course_data,
data,
out_dir,
force=cfg['force'])
# ebook
ebook_name = self._title(course_data)
if not cfg['source_only']:
fn = os.path.join(out_dir, ebook_name) + '.mobi'
if course_data['is_finish'] and os.path.isfile(fn):
sys.stdout.write("{} exists\n".format(ebook_name))
else:
src_dir = os.path.join(out_dir, course_data['column_title'])
make_mobi(source_dir=src_dir, output_dir=out_dir)
# push to kindle
if cfg['push'] and not cfg['source_only']:
fn = os.path.join(out_dir, "{}.mobi".format(ebook_name))
try:
send_to_kindle(fn, cfg)
sys.stdout.write("push to kindle done\n")
except Exception as e:
sys.stderr.write(
"ERROR: push to kindle failed, e={}\n".format(e))
