def replace_file_content(file_path):
"""
替换知乎中的中转链接
:param file_path: 替换的文件路径
:return:
"""
file_content = u_file.read_content(file_path)
# text = '<a href="https://link.zhihu.com/?target=http%3A//index.iresearch.com.cn/pc" class=" wrap external">'
replace_content = re.sub(
r'href="[^"]+"', lambda match: unquote(
match.group(0).replace('https://link.zhihu.com/?target=', '')),
file_content)
u_file.write_content(
r'D:\forme\Git_Projects\python-base\tool\industry-analysis-'
r'report-replace.html', replace_content)
def build_content_html():
target_album_id = 4815905
track_infos = get_album_track_info_from_cache(target_album_id)
template_content = u_file.get_content(r'cache\template.html')
content = ''
for track_info in track_infos:
if track_info.get('title').find('坂本真绫') < 0:
u_log.info('The track is not need. title: {}'.format(track_info.get('title')))
continue
if track_info.get('title').find('合集') >= 0:
u_log.info('The track is collection. title: {}'.format(track_info.get('title')))
continue
content += '\n\n<h2>' + track_info.get('title') + '</h2>\n\n'
content += track_info.get('richIntro')
template_content.replace('{content}', content)
u_file.write_content(r'cache\target.html', content)
def output_course_list(course_data_path: str):
course_info = u_file.load_json_from_file(course_data_path)
template = u_file.read_content(r'cache/template.html')
html_content = '<ul>\n'
for stage_course in course_info['stageCourses']:
html_content += '<li>' + stage_course['courseName']
# 如果有题目的话，列出题目
questions = stage_course['questions']
if len(questions) > 0:
html_content += '\n<ul>'
for question in questions:
# question_detail_content = question['detail']['content']
html_content += '<li>' + question['name'] + '---' + question['summary'] + '\n'
html_content += '</ul>'
html_content += '</li>\n'
html_content += '</ul>'
template = template.replace('{{title}}', course_info['name'])
template = template.replace('{{content}}', html_content)
u_file.write_content(r'cache\output.html', template)
def output_course_chapter_notes(name):
course_data_path = r'cache\course-info-{}.json'.format(name)
course_info = u_file.load_json_from_file(course_data_path)
content = '# {}\n\n'.format(name)
log.info('stage_course size: {}'.format(len(course_info['stageCourses'])))
for stage_course in course_info['stageCourses']:
chapters = stage_course['chapters']
content += '## {}\n\n'.format(stage_course['courseName'])
log.info('course {} chapters size: {}'.format(stage_course['courseName'], len(chapters)))
if len(chapters) <= 0:
continue
# 遍历每一章节
for chapter in chapters:
content += '\n### {}\n\n'.format(chapter['name'])
periods = chapter['periods']
log.info('chapter: {}, periods size: {}'.format(chapter['name'], len(periods)))
if len(periods) <= 0:
continue
# 遍历每个视频讲解
for period in periods:
# 获取笔记并保存
content += '\n#### {}\n\n'.format(period['name'])
notes = get_video_notes(period['id'])
log.info('period: {}, notes size: {}'.format(period['name'], len(notes)))
if len(notes) <= 0:
log.info('The period: {}, notes is empty.'.format(period['name']))
continue
for note in notes:
if len(note['content']) <= 5:
log.info('The note is short: {}'.format(note['content']))
continue
content += note['content'] + '\n---------{}\n'.format(note['likeNum'])
u_file.write_content(r'cache\output-note-{}.md'.format(name), content)
u_file.write_content(r'cache\output-note-{}.md'.format(name), content)
def output_course_question(name):
course_data_path = r'cache\course-info-{}.json'.format(name)
course_info = u_file.load_json_from_file(course_data_path)
template = u_file.read_content(r'cache/template.html')
html_content = ''
for stage_course in course_info['stageCourses']:
html_content += '<h1><a href="{}" target="_blank">{}</a></h1>\n'\
.format(stage_course['url'], stage_course['courseName'])
# 如果有题目的话，列出题目
questions = stage_course['questions']
if len(questions) > 0:
for question in questions:
# question_detail_content = question['detail']['content']
html_content += '<h4><a href="{}" target="_blank">{}</a></h4>\n'\
.format(question['url'], question['title'])
# html_content += question['detail']['content']
template = template.replace('{{title}}', course_info['name'])
template = template.replace('{{content}}', html_content)
u_file.write_content(r'cache\output-title-{}.html'.format(name), template)
def generate_gitbook_summary(source_dir):
"""
生成gitbook的summary目录文件，通过遍历文件目录树实现
:param source_dir: source_dir
:return:
"""
sub_file_paths = u_file.get_all_sub_files(source_dir, contain_dir=True)
summary_content = ''
sub_file_paths.sort()
exclude_paths = [
'.git', '.idea', 'assets', 'temp', 'node_modules', '_book'
]
for sub_file_path in sub_file_paths:
relative_path = sub_file_path.replace(source_dir + '\\', '')
# 过滤掉非markdown文件
ignore = False
for exclude_path in exclude_paths:
if sub_file_path.find(exclude_path) >= 0:
ignore = True
if ignore:
continue
path_depth = relative_path.count('\\')
menu = ' ' * path_depth
if os.path.isfile(sub_file_path):
if sub_file_path.find('.md') >= 0:
menu += '- [{}]({})'.format(
os.path.split(relative_path)[1].replace('.md', ''),
relative_path)
else:
continue
else:
menu += '- {}'.format(relative_path.split('\\')[-1])
summary_content += menu + "\n"
u_file.write_content(r'cache\result.md', summary_content)
print(summary_content)
def test_read_write_file():
content = '--something--'
file_path = r'cache\test.dat'
file_path = os.path.abspath(file_path)
u_file.write_content(file_path, content)
u_unittest.assert_eq(content, u_file.read_content(file_path))