")[0]
- album_title = text.extract(page, '
', '')[0]
-
- # grab the id out of the title (handiest place to get it)
- htmltitle = text.extract(page, '
', '')[0]
- album_id = text.extract(htmltitle, '#', ' ')[0]
-
- # tags
- taghunk = text.extract(page, '
')
- tags = re.compile(r"\s- ([\d\w ]+)").findall(taghunk[0])
album_data = {
- "album": {
- "id": album_id,
- "title": title
- },
- "date": None,
- "title": title,
- "tags": tags,
+ "album_id" : album_id,
+ "album_title": text.extr(page, "
", "<"),
+ "tags" : text.split_html(text.extr(
+ page, '')[0]
- findall = re.compile(self.pattern).findall
- pages = findall(pagination)
+ while True:
+ container = text.extr(page, '', '')
+ for url in text.extract_iter(
+ container, '', '')[0]
- for url in text.extract_iter(image_container, '