描述

pirate 是由我的 django 脚手架 original 实现的，文件上传提供了七牛和腾讯云两个 backend，部署提供了默认的配置文件，因此只要关注具体的微信的抓取逻辑即可。

核心表讲解

pirate/original/extracter/models.py

微信文章表，正常设计，大字段拆表。

13 class WXArticle(TimeStampedModel):

14 raw_url = models.CharField(max_length=1023)

15 title = models.CharField(max_length=255)

16 cover = models.CharField(max_length=255)

17 description = models.CharField(max_length=255, default='')

18 is_active = models.BooleanField(default=False)

19 is_delete = models.BooleanField(default=False)

98 class WXArticleContent(TimeStampedModel):

99 article_id = models.IntegerField(unique=True)

100 content = models.TextField()

101 body_script = models.TextField(default='')

pirate/original/extracter/models.py

图片上传缓存表，因为有时候会重复抓取一篇文章(例如编辑后需要重新写文章)，而每次抓取文章时会将里面的图片上传到我们的 cdn，添加上传文件缓存表来减少重复的图片上传操作。

188 class URLFileUploadCache(TimeStampedModel):

189 raw_url = models.CharField(blank=True, default='', max_length=512)

190 url = models.CharField(blank=True, default='', max_length=255)

191 raw_url_md5 = models.CharField(blank=True, default='', max_length=64, db_index=True)

抓取

观察微信文章发现，文章 div id=js_content 为文章正文，其中标题和 cover 图在 meta 里面，使用 requests 抓取文章原文，BeautifulSoup 过滤需要的 dom，正则找出需要替换的图片，upload_handler 选择七牛去上传图片并且替换掉原图地址。

21 @classmethod

22 def spider_url(cls, raw_url):

23 assert raw_url.startswith('https://mp.weixin.qq.com/') or raw_url.startswith('http://mp.weixin.qq.com/')

24 content = tools.spider_request(raw_url)

25 description = content_text = title = cover = ''

26 body_script = ''

27 if content:

28 b = BeautifulSoup(content, 'html.parser')

29 content_dom = b.find('div', id='js_content')

30 title_dom = b.find('meta', property="og:title")

31 cover_dome = b.find('meta', property="og:image")

32 if title_dom:

33 title = title_dom.attrs['content']

34 if cover_dome:

35 cover = cover_dome.attrs['content']

36 raw_url = cover

37 upload_cache = URLFileUploadCache.get_cached_objects(raw_url, get_last=True)

38 if upload_cache:

39 cover = upload_cache[0].url

40 else:

41 upload_data = tools.upload_file_from_url(raw_url)

42 url = upload_data['url']

43 if url:

44 URLFileUploadCache.new_cache(raw_url, url)

45 cover = url

46 if content_dom:

47 content_text = unicode(content_dom)

48 ss = b.body.find_all('script')

49 body_script = ''.join(unicode(s) for s in ss)

50 urls = []

51 for _re in constants.WEIXIN_IMAGE_RES:

52 urls.extend(_re.findall(content_text))

53 descriptions = constants.WEIXIN_DESCRIPTION_RE.findall(content)

54 if descriptions:

55 description = BeautifulSoup(descriptions[0]).meta.attrs.get('content', '')

56 mapper = {}

57 for raw_url in urls:

58 if raw_url in mapper:

59 continue

60 upload_cache = URLFileUploadCache.get_cached_objects(raw_url, get_last=True)

61 if upload_cache:

62 mapper[raw_url] = upload_cache[0].url

63 else:

64 upload_data = tools.upload_file_from_url(raw_url, )

65 url = upload_data['url']

66 if url:

67 URLFileUploadCache.new_cache(raw_url, url)

68 mapper[raw_url] = url

69 for raw_url, url in mapper.iteritems():

70 if not url:

71 continue

72 content_text = content_text.replace(raw_url, url)

73 return {

74 'raw_url': raw_url,

75 'title': title,

76 'cover': cover,

77 'content': content_text,

78 'description': description,

79 'body_script': body_script,

80 }

上传文件到七牛的 upload_handler

13 POLICY = settings.FILE_CALLBACK_POLICY or {

14 'callbackUrl': settings.FILEUPLOAD_CALLBACK_URL,

15 'callbackBody': 'bucket=$(bucket)&key=$(key)&filename=$(fname)&filesize=$(fsize)',

16 'insertOnly': 1,

17 }

18

19

20 class UploadHandler(object):

21

22 def __init__(self, key, secret, bucket):

23 self.key = key

24 self.secret = secret

25 self.bucket = bucket

26 self.backend = qiniu

27 self._backend_auth = Auth(self.key, self.secret)

28

29 def _upload_token(self, key, expires=3600, policy=None):

30 token = self._backend_auth.upload_token(self.bucket, key=key, expires=expires, policy=policy)

31 return token

32

33 def upload_file(self, key, data, policy=None, fname='file_name'):

34 if policy is None:

35 policy = POLICY

36 uptoken = self._upload_token(key, policy=policy)

37 return self.backend.put_data(uptoken, key, data, fname=fname)

38

39 def get_download_url(self, key):

40 return '{}{}'.format(settings.FILE_DOWNLOAD_PREFIX, key)

CDN 配置

创建一个公开的存储空间，名字即 FILE_UPLOAD_BUCKET

为了让域名好看一些，配置 CDN 加速域名，根据步骤操作即可(有一些 dns 的操作)。FILE_DOWNLOAD_PREFIX

个人中心秘钥管理获取 upload_handler 需要的 FILE_UPLOAD_KEY、FILE_UPLOAD_SECRET

执行部署

创建对应 mysql 数据库

创建 virtualenv，source 后 pip install 项目路径下的 requirements/base.txt

创建 config/settings/private_production.py，见下面代码段

数据库 migrate，cd 到 original 目录，执行./manage.py migrate --settings=config.settings.production

启动项目 ./manage.py runserver 0.0.0.0:8976 (端口号随意)

当然建议用 supervisor + nginx，见deploy目录下的相关例子

import os

DATABASES = {

'default': {

'ENGINE': 'django.db.backends.mysql',

'NAME': 'dbname', # 改成你的数据库名字

'HOST': os.environ.get('ORIGINAL_MYSQL_HOST', 'localhost'), # 数据库host

'USER': os.environ.get('ORIGINAL_MYSQL_USER', 'db_username'), # 改成你的数据库user

'PASSWORD': os.environ.get('ORIGINAL_MYSQL_PASSWORD', 'db_password'), # 改成你的数据库password

'PORT': os.environ.get('ORIGINAL_MYSQL_PORT', 3306),

'OPTIONS': {'charset': 'utf8mb4'},

}

}

FILE_UPLOAD_BACKEND = 'qiniu'

FILE_UPLOAD_KEY = 'i6fdSECQjLfF' # 改成你的qiniu key，现在这里是假的

FILE_UPLOAD_SECRET = 'adfiuerqp' # 改成你的qiniu secret

FILE_UPLOAD_BUCKET = 'reworkdev' # 改成你的qiniu bucket

FILE_CALLBACK_POLICY = {}

FILE_DOWNLOAD_PREFIX = '' # 改成你的host, 例如 http://cdn.myhost.com/

FILEUPLOAD_CALLBACK_URL = # 改成你自己host的对应地址, 例如 https://www.myhost.com/api/v1/file/upload/callback/

postman 测试接口

查看数据库

接下来

基本物料接口准备就绪，下面就可以正式开始 Java 框架的学习。