def get_authors_info(author_url):
"""
获取发帖, 回帖作者的个人信息
"""
uuid = author_url.split('/')[-1]
author = Author()
author.author_uuid = uuid
sel = Selector(
text=requests.get("https://me.csdn.net/" + uuid, headers=HEADERS).text)
name = ""
for item in sel.xpath("//div[@class='lt_title']/text()").extract():
name += item.strip()
author.name = name
author.original_blog_nums = int(
sel.xpath("//div[@class='me_chanel_det_item access']//span/text()").
extract()[0].strip())
author.desc = sel.xpath(
"//div[@class='description clearfix']//p/text()").extract()[0].strip()
author.rank = sel.xpath(
"//div[@class='me_chanel_det_item access']//span/text()").extract(
)[1].strip()
author.follower_nums = sel.xpath(
"//div[@class='fans']//a//span/text()").extract()[0].strip()
author.following_nums = sel.xpath(
"//div[@class='att']//a//span/text()").extract()[0].strip()
sel = Selector(
text=requests.get("https://me.csdn.net/bbs/" +
uuid, headers=HEADERS).text)
author.post_topic_nums = sel.xpath(
"//div[@class='me_chanel_det_item access']//span/text()").extract(
)[0].strip()
author.answer_topic_nums = sel.xpath(
"//div[@class='me_chanel_det_item access']//span/text()").extract(
)[1].strip()
author.end_topic_percentage = sel.xpath(
"//div[@class='me_chanel_det_item access']//span/text()").extract(
)[2].strip()
sel = Selector(text=requests.get("https://me.csdn.net/bbs/ask/" + uuid,
headers=HEADERS).text)
author.post_question_nums = sel.xpath(
"//div[@class='me_chanel_det_item access']//span/text()").extract(
)[0].strip()
author.answer_question_nums = sel.xpath(
"//div[@class='me_chanel_det_item access']//span/text()").extract(
)[1].strip()
if Author.select().where(Author.author_uuid == author.author_uuid):
author.save()
else:
author.save(force_insert=True)
