def gather_info(url, course_path):
''' gather course information. '''
soup = create_soup(url)
course_title = soup.find('h1', {"class": "default-title"}).text
course_ids = soup.findAll(
'div', {"data-course-id": True}) # find all course id attributes
course_id = course_ids[0][
'data-course-id'] # select the first course id attribute value
author_name = soup.find('cite', {"data-ga-label": "author-name"}).text
#topic tags
topic_tags = soup.findAll('a', {"data-ga-label": "topic-tag"})
topic_tag = '\t'
for tag in topic_tags:
topic_tag += '#' + tag.text + '\t'
#software tags
software_tags = soup.findAll('a', {"data-ga-label": "software-tag"})
software_tag = ''
for tag in software_tags:
software_tag += '#' + tag.text + '\t'
release_date = soup.find('span', {"id": "release-date"}).text
duration = soup.find('div', {"class": "duration"}).find('span').text
download_date = time.strftime("%d/%m/%y") # todays date
if soup.find('span', {"id": "update-date"}) != None:
update_date = soup.find('span', {"id": "update-date"}).text
else:
update_date = release_date
message.write("Course Name", course_title)
message.write("Course id", course_id)
message.write("Author Name", author_name)
message.write("Topics", topic_tag)
message.write("Softwares", software_tag)
message.write("Duration", duration)
message.write("Release Date", release_date)
message.write("Updated On", update_date)
message.write("Course URL", url)
os.chdir(course_path)
with open('info.txt', 'a') as info_file:
info_file.writelines('Course Name' + '\t\t' + course_title + '\n')
info_file.writelines('Course id' + '\t\t' + course_id + '\n')
info_file.writelines('Author Name' + '\t\t' + author_name + '\n')
info_file.writelines('Topics' + '\t\t' + topic_tag + '\n')
info_file.writelines('Softwares' + '\t\t' + software_tag + '\n')
info_file.writelines('Duration' + '\t\t' + duration + '\n')
info_file.writelines('Release Date' + '\t\t' + release_date + '\n')
info_file.writelines('Updated On' + '\t\t' + update_date + '\n')
info_file.writelines('Downloaded On' + '\t\t' + download_date + '\n')
info_file.writelines('Course URL' + '\t\t' + url + '\n')
info_file.close()
with open('CONTENT.md', 'a') as content_md:
content_md.writelines("# " + course_title + " with " + author_name +
" on lynda.com \n\n")
content_md.writelines("## Chapters:\n\n") # next heading
content_md.close()
# print message
message.print_line(message.INFO_FILE_CREATED)
def info_file(url, course_path):
''' gather course information. '''
soup = create_soup(url)
course_title = soup.find('h1', {"class": "default-title"}).text
course_ids = soup.findAll(
'div', {"data-course-id": True}) # find all course id attributes
course_id = course_ids[0][
'data-course-id'] # select the first course id attribute value
author_name = soup.find('cite', {"data-ga-label": "author-name"}).text
#topic tags
topic_tags = soup.findAll('a', {"data-ga-label": "topic-tag"})
topic_tag = '\t'
for tag in topic_tags:
topic_tag += '#' + tag.text + '\t'
#software tags
software_tags = soup.findAll('a', {"data-ga-label": "software-tag"})
software_tag = ''
for tag in software_tags:
software_tag += '#' + tag.text + '\t'
if software_tag == '':
software_tag += 'None'
release_date = soup.find('span', {"id": "release-date"}).text
duration = soup.find('div', {"class": "duration"}).find('span').text
download_date = time.strftime("%d/%B/%Y") # todays date
message.write("\nCourse Name", course_title)
message.write("Course id", course_id)
message.write("Author Name", author_name)
message.write("Topics", topic_tag)
message.write("Softwares", software_tag)
message.write("Duration", duration)
message.write("Release Date", release_date)
message.write("Downloaded On", download_date)
message.write("Course URL", url)
os.chdir(course_path) # Jump to course directory to save info.txt
# write to info.txt
info_file = io.open('info.txt', mode="a", encoding="utf-8")
info_file.writelines(u'Course Name' + '\t\t' + course_title + '\n')
info_file.writelines(u'Course id' + '\t\t' + course_id + '\n')
info_file.writelines(u'Author Name' + '\t\t' + author_name + '\n')
info_file.writelines(u'Topics' + '\t\t' + topic_tag + '\n')
info_file.writelines(u'Softwares' + '\t\t' + software_tag + '\n')
info_file.writelines(u'Duration' + '\t\t' + duration + '\n')
info_file.writelines(u'Release Date' + '\t\t' + release_date + '\n')
info_file.writelines(u'Downloaded On' + '\t\t' + download_date + '\n')
info_file.writelines(u'Course URL' + '\t\t' + url + '\n')
info_file.close()
# write to content.md
content_md = io.open('CONTENT.md', mode="a", encoding="utf-8")
content_md.writelines(u"# " + course_title + " with " + author_name +
" on lynda.com \n")
content_md.close()
# print message
message.print_line(message.INFO_FILE_CREATED)