def add_postcast_feed(feed_obj):
"""
播客类型的 RSS 源
:param feed_obj:
:return: 解析结果，成功字典；失败 None
"""
url = feed_obj.url
if feed_obj.feed.get('title'):
name = get_hash_name(url)
site = Site.objects.filter(name=name, status='active')
if site:
logger.info(f"源已经存在：`{url}")
return {"site": site[0].pk}
cname = feed_obj.feed.title[:50]
try:
link = feed_obj.feed.content_detail.base
except AttributeError:
if feed_obj.feed.get('link'):
link = feed_obj.feed.link[:1024]
else:
link = url
if feed_obj.feed.get('subtitle'):
brief = trim_brief(get_html_text(feed_obj.feed.subtitle))[:200]
else:
brief = feed_obj.feed.title
try:
author = feed_obj.feed.author_detail.name
except AttributeError:
author = feed_obj.feed.get('author') or get_short_host_name(link)
# 使用默认头像
if feed_obj.feed.get('image'):
favicon = save_avatar(feed_obj.feed.image.href, name)
else:
favicon = generate_rss_avatar(link)
try:
site = Site(name=name, cname=cname, link=link, brief=brief, star=10, copyright=30,
creator='podcast', rss=url, favicon=favicon, author=author)
site.save()
return {"site": site.pk}
except:
logger.error(f'新增播客异常：`{url}')
else:
logger.warning(f"播客解析失败：`{url}")
return None
def save_feed_to_db(name, cname, link, avatar, brief, url):
site = Site.objects.filter(name=name)
if site:
logger.info(f"源已经存在：`{url}")
return {"site": site[0].pk}
else:
# 新增站点
if avatar:
favicon = save_avatar(avatar, name, referer=url)
else:
favicon = get_random_emoji()
try:
site = Site(name=name, cname=cname, link=link, brief=brief, star=12, creator='wemp', copyright=20,
rss=url, favicon=favicon)
site.save()
return {"site": site.pk}
except:
logger.warning(f'新增公众号失败：`{name}')
return None
def parse_wemp_ershicimi(url, update=False):
"""
解析微信公众号，www.ershicimi.com
:param url: 公众号主页地址
:param update: 如果已经存在，是否更新
:return: 解析结果，成功返回字典；失败 None
"""
rsp = get_with_proxy(url)
if rsp is None:
return None
if rsp.ok:
response = HtmlResponse(url=url, body=rsp.text, encoding='utf8')
qrcode = response.selector.xpath(
"//img[@class='qr-code']/@src").extract_first()
if qrcode:
name = urllib.parse.parse_qs(
urllib.parse.urlparse(qrcode).query)['username'][0]
if name:
site = Site.objects.filter(name=name)
if site:
logger.info(f"源已经存在：`{url}")
return {"site": site[0].pk}
else:
# 新增站点
cname = response.selector.xpath("//li[@class='title']//span[@class='name']/text()").\
extract_first().strip()
avatar = response.selector.xpath(
"//img[@class='avatar']/@src").extract_first().strip()
favicon = save_avatar(avatar, name)
brief = response.selector.xpath(
"//div[@class='Profile-sideColumnItemValue']/text()"
).extract_first().strip()
if cname and avatar and brief:
try:
site = Site(name=name,
cname=cname,
link=qrcode,
brief=brief,
star=9,
creator='wemp',
copyright=20,
rss=url,
favicon=favicon)
site.save()
except:
logger.warning(f'新增公众号失败：`{name}')
# 是否需要更新内容
if update:
try:
site = Site.objects.get(name=name)
links = response.selector.xpath(
"//*[@class='weui_media_title']/a/@href").extract(
)[:10]
for link in links:
link = urllib.parse.urljoin(url, link)
wemp_spider(link, site)
set_updated_site(site.pk, ttl=12 * 3600)
except:
logger.warning(f'更新公众号内容出现异常：`{name}')
return {"site": site.pk}
else:
logger.warning(f'微信公众号 id 解析失败：`{qrcode}')
else:
logger.warning(f'二维码链接解析失败：`{url}')
return None
def github_callback(request):
"""
接收 github 的登录回调
"""
try:
code = request.GET.get('code')
if code:
rsp = requests.post('https://github.com/login/oauth/access_token',
data={
"client_id": settings.GITHUB_OAUTH_KEY,
"client_secret":
settings.GITHUB_OAUTH_SECRET,
"code": code,
},
headers={"Accept": "application/json"},
timeout=10)
if rsp.ok:
access_token = rsp.json().get('access_token')
if access_token:
rsp = requests.get('https://api.github.com/user',
headers={
"Accept":
"application/json",
"Authorization":
f"token {access_token}",
},
timeout=10)
if rsp.ok:
if rsp.json().get('id'):
oauth_id = f'github/{rsp.json()["id"]}'
oauth_name = rsp.json().get(
'name') or rsp.json().get('login')
oauth_avatar = rsp.json().get('avatar_url')
oauth_email = rsp.json().get('email')
oauth_blog = rsp.json().get(
'blog') or rsp.json().get('html_url')
oauth_ext = json.dumps(rsp.json())
# 用户信息入库
user, created = User.objects.update_or_create(
oauth_id=oauth_id,
defaults={
"oauth_name": oauth_name,
"oauth_avatar": oauth_avatar,
"oauth_email": oauth_email,
"oauth_blog": oauth_blog,
"oauth_ext": oauth_ext,
})
if created:
logger.warning(f"欢迎新用户登录：`{user.oauth_name}")
add_user_sub_feeds(
oauth_id,
get_visitor_subscribe_feeds('',
'',
star=28))
add_register_count()
# 用户头像存储到本地一份，国内网络会丢图
avatar = save_avatar(oauth_avatar, oauth_id)
user.avatar = avatar
user.save()
response = redirect('index')
response.set_signed_cookie('oauth_id',
oauth_id,
max_age=10 * 365 *
86400)
response.set_signed_cookie('toast',
'LOGIN_SUCC_MSG',
max_age=20)
return response
except (ConnectTimeout, HTTPError, ReadTimeout, Timeout, ConnectionError):
logger.warning("OAuth 认证网络出现异常！")
except:
logger.error("OAuth 认证出现未知异常")
response = redirect('index')
response.set_signed_cookie('toast', 'LOGIN_ERROR_MSG', max_age=20)
return response
def parse_wemp_ershicimi(url):
"""
解析微信公众号，www.ershicimi.com
:param url: 公众号主页地址
:return: 解析结果，成功返回字典；失败 None
"""
try:
rsp = requests.get(url, timeout=10)
except:
logger.warning(f'请求出现异常：`{url}')
return None
if rsp.ok:
response = HtmlResponse(url=url, body=rsp.text, encoding='utf8')
qrcode = response.selector.xpath(
"//img[@class='qr-code']/@src").extract_first()
if qrcode:
name = urllib.parse.parse_qs(
urllib.parse.urlparse(qrcode).query)['username'][0]
if name:
if not Site.objects.filter(name=name).exists():
# 新增站点
cname = response.selector.xpath("//li[@class='title']//span[@class='name']/text()").\
extract_first().strip()
avatar = response.selector.xpath(
"//img[@class='avatar']/@src").extract_first().strip()
favicon = save_avatar(avatar, name)
brief = response.selector.xpath(
"//div[@class='Profile-sideColumnItemValue']/text()"
).extract_first().strip()
if cname and avatar and brief:
try:
site = Site(name=name,
cname=cname,
link=qrcode,
brief=brief,
star=19,
freq='日更',
creator='wemp',
copyright=20,
tag='公众号',
rss=url,
favicon=favicon)
site.save()
except:
logger.warning(f'新增公众号失败：`{name}')
else:
# 更新内容
try:
site = Site.objects.get(name=name)
wemp_links = response.selector.xpath(
"//*[@class='weui_media_title']/a/@href").extract(
)[:3]
wemp_spider(wemp_links, site)
except:
logger.warning(f'更新公众号内容出现异常：`{name}')
return {"name": name}
else:
logger.warning(f'微信公众号 id 解析失败：`{qrcode}')
else:
logger.warning(f'二维码链接解析失败：`{url}')
return None
