def download_story(self, start_chapter=None, stop_chapter=None, exit_on_error=EXIT_ON_ERROR,
download_bonus_chapter=DOWNLOAD_BONUS_CHAPTER, chapter_list_ascending=CHAPTER_LIST_ASCENDING):
"""
:param start_chapter:
:param stop_chapter:
:param exit_on_error:
:param download_bonus_chapter: Do not download 'Bonus' chapters if False
:param chapter_list_ascending: chapter name order will be ascending
:return:
Story initial check => Return if failure
Reverse chapter (if any) => chapter name order will be ascending
Get download range (from start_chapter to stop_chapter)
Import story to mongo (name only)
Loop through story_download_range
Download bonus chapter (if any or match condition)
Call self.download_a_chapter and append result to 'story_result'
Stop downloading on failure if 'exit_on_error' is True and chapter_result's status is False
"""
utils.mkdir(self.story_dir)
if 'Story data is invalid' in self.story_init_check().keys():
return self.story_init_check()
if not chapter_list_ascending:
self.chapter_list['summary'].reverse()
story_download_range = self.get_story_download_range(start_chapter, stop_chapter)
if story_download_range is not None:
self.mongo_instance.import_story(opt_xpath={self.site_url: self.opt_xpath})
for chapter_name in story_download_range:
if not download_bonus_chapter and 'Bonus' in chapter_name:
continue
self.story_result[chapter_name] = self.download_a_chapter(chapter_name=chapter_name, start_page=1)
if exit_on_error and not self.story_result[chapter_name]['status']:
print "%s : Failed to download chapter %s" % (self.story_url, chapter_name)
break
return self.story_result
else:
print "Story {0} - Failed to get download range : {1}".format(self.story_name, self.story_url)
return {'Story data is invalid': 'Failed to get download range'}
def chapter_download(self, move_chapter_to_img_dir=True):
"""
:param move_chapter_to_img_dir: Move downloaded chapter to image dir
:return: chapter_result
:type return: dict()
Validate page_list: if unable to get or is null => Return default chapter_result
Remove self.chapter_dir : Make sure all old files will be deleted
Append all pages to threading and run
Validate chapter after downloading
Move chapter to img_dir and import result to mongodb
"""
if self.page_list == list():
return self.chapter_result
utils.rmdir(self.chapter_dir)
utils.mkdir(self.chapter_dir)
page_number = int(self.start_page)
print "\nDOWNLOADING Story : {0} - chapter-{1} - site_url {2} - {3} pages"\
.format(self.story.story_name, self.chapter_name, self.story.site_url, len(self.page_list))
# Enable this for debug only
# if self.story.site_url == 'blogtr' and self.chapter_name == '2':
# self.page_list.append("-0S2VlsSH424/UTqPDOXh7HI/AAAAAAAAAZg/P2gifiG1dEo")
threads = list()
for page_url in self.page_list:
page = Page(self, page_number=page_number, page_url=page_url)
thread = threading.Thread(target=page.page_download, args=(self.chapter_result,))
threads.append(thread)
page_number += 1
utils.threading_run(threads=threads)
self.validate_chapter()
if self.chapter_result['status']:
if move_chapter_to_img_dir:
self.chapter_result['status'] = self.do_move_chapter_to_img_dir()
self.import_chapter_to_mongo()
return self.chapter_result
