def img_upload(self, markdowncontent, content):
# 图片需要上传到 csdn，否则发布的文章没有图片
upload_url = 'https://bizapi.csdn.net/blog-console-api/v3/image/transfer'
content_html = etree.HTML(content)
src_list = content_html.xpath('//img/@src')
for src in src_list:
while 1:
time_stamp = int(time.time() * 1000)
salt = self.gen_random()
form_data = {"uuid": f"img-{salt}-{time_stamp}", "url": src}
base_url = "/blog-console-api/v3/image/transfer"
self.sess.headers = headers_to_dict(
self.gen_header(base_url, method='POST'))
res = self.sess.post(url=upload_url, json=form_data)
if res.text:
r_json = res.json()
# 图片在文章中本来就不存在
if r_json.get('code') == 400:
return markdowncontent, content
img_url = r_json.get('data').get('img_url')
content = content.replace(src, img_url)
markdowncontent = markdowncontent.replace(src, img_url)
time.sleep(random.random() * 0.1)
break
# else:
# print("请求响应为空：")
# print(res.text, res.cookies.get_dict(), res.status_code)
return markdowncontent, content
def img_upload(self, content, referer):
img_header = f"""
accept: */*
accept-encoding: gzip, deflate, br
accept-language: zh-CN,zh;q=0.9
x-requested-with:fetch
cookie: {self.cookie}
origin: https://zhuanlan.zhihu.com
referer: {referer}
user-agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.150 Safari/537.36
"""
# 图片需要上传到 csdn，否则发布的文章没有图片
upload_url = 'https://zhuanlan.zhihu.com/api/uploaded_images'
self.sess.headers = headers_to_dict(img_header)
content_html = etree.HTML(content)
src_list = content_html.xpath('//img/@src')
for src in src_list:
while 1:
files = {'url': (None, src), 'source': (None, 'article')}
res = self.sess.post(url=upload_url, files=files)
# print('上传图片结果：', res.text)
if res.text:
r_json = res.json()
# 图片在文章中本来就不存在
if r_json.get('code') == 400:
return content
img_url = r_json.get('watermark_src')
content = content.replace(src, img_url)
time.sleep(random.random() * 0.1)
break
return content
def __init__(self, cookie):
"""
@param cookie:
"""
self.sess = requests.session()
base_header = f"""
"""
self.sess.headers = headers_to_dict(base_header)
def get_category(self):
get_category_url = 'https://bizapi.csdn.net/blog-console-api/v3/editor/getBaseInfo'
base_url = '/blog-console-api/v3/editor/getBaseInfo'
self.sess.headers = headers_to_dict(
self.gen_header(base_url, method='GET'))
res = self.sess.get(get_category_url)
if res.text and res.status_code == 200:
categoty_list = res.json().get('data').get('categorys')
return categoty_list
return None
def __init__(self, cookie):
self.sess = requests.session()
base_header = f"""
accept-encoding: gzip, deflate, br
accept-language: zh-CN,zh;q=0.9
cookie: {cookie}
referer: https://i.cnblogs.com/posts/edit
user-agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.150 Safari/537.36
"""
self.sess.headers = headers_to_dict(base_header)
edit_url = 'https://i.cnblogs.com/posts/edit'
res_edit = self.sess.get(edit_url)
self.xsrf_token = res_edit.cookies.get_dict().get('XSRF-TOKEN')
def __init__(self, cookie):
self.sess = requests.session()
base_header = f"""
accept: */*
accept-encoding: gzip, deflate, br
accept-language: zh-CN,zh;q=0.9
content-type: application/json
cookie: {cookie}
origin: https://juejin.cn
referer: https://juejin.cn/
user-agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.150 Safari/537.36
"""
self.sess.headers = headers_to_dict(base_header)
def publish_content(self, tags, title, markdowncontent, content,
plant_config):
self.markdowncontent, self.content = self.img_upload(
markdowncontent=markdowncontent, content=content)
base_url = "/blog-console-api/v3/mdeditor/saveArticle"
self.sess.headers = headers_to_dict(
self.gen_header(base_url, method='POST'))
url = 'https://bizapi.csdn.net/blog-console-api/v3/mdeditor/saveArticle'
if not tags and not plant_config:
return False
if not tags:
tags = plant_config[0].tags
type_name = 'original'
original_link = ''
readType = 'public'
if plant_config:
type = plant_config[0].art_type
art_pub_type = plant_config[0].art_publish_type
if art_pub_type == 1:
readType = 'public'
elif art_pub_type == 2:
readType = 'private'
elif art_pub_type == 3:
readType = 'read_need_vip'
if type == 1:
type_name = 'original'
elif type == 2:
type_name = 'repost'
original_link = plant_config[0].art_source_url
elif type == 3:
type_name = 'translated'
original_link = plant_config[0].art_source_url
form_data = {
"title": title,
"markdowncontent": self.markdowncontent,
"content": self.content,
"readType": readType, # 私密private vip可见 read_need_vip
"tags": tags,
"status": 0,
"categories":
plant_config[0].category_value if plant_config else "",
"type": type_name,
"original_link": original_link,
"authorized_status": True if original_link else False,
"not_auto_saved": "1",
"source": "pc_mdeditor"
}
res = self.sess.post(url=url, json=form_data)
if res.text:
return res.text
return None
def del_doc(self, art_url: str):
art_id = art_url.rsplit('/', 1)[1]
del_url = 'https://bizapi.csdn.net/blog-console-api/v1/article/del'
base_url = "/blog-console-api/v1/article/del"
self.sess.headers = headers_to_dict(
self.gen_header(base_url, method='POST'))
form_data = {"article_id": art_id, "deep": "false"}
res = self.sess.post(del_url, json=form_data)
if res.text:
r_json = res.json()
code = r_json.get('code')
msg = r_json.get('msg')
if code == 200 and msg == "success":
return True
return False
def __init__(self, cookie):
"""
@param cookie:
"""
self.sess = requests.session()
base_header = f"""
Accept: application/json
Accept-Encoding: gzip, deflate, br
Accept-Language: zh-CN,zh;q=0.9
Cookie: {cookie}
Host: www.jianshu.com
Origin: https://www.jianshu.com
Referer: https://www.jianshu.com/writer
User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.150 Safari/537.36
"""
self.sess.headers = headers_to_dict(base_header)
def __init__(self, seg_token):
seg_token = cookie_to_dict(seg_token).get('PHPSESSID')
self.sess = requests.session()
base_header = f"""
accept: */*
accept-encoding: gzip, deflate, br
accept-language: zh-CN,zh;q=0.9
content-type: application/json
cookie: 123
token: {seg_token}
origin: https://segmentfault.com
referer: https://segmentfault.com/
user-agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.150 Safari/537.36
"""
self.sess.headers = headers_to_dict(base_header)
def upload_img(self, content):
upload_head = """
accept: application/json
accept-language: zh-CN,zh;q=0.9
origin: https://www.jianshu.com
referer: https://www.jianshu.com/
user-agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.150 Safari/537.36
"""
upload_url = 'https://upload.qiniup.com/'
md = markdown.Markdown(extensions=[
'markdown.extensions.extra', 'markdown.extensions.codehilite'
])
content_html = md.convert(content)
res_html = etree.HTML(content_html)
src_list = res_html.xpath('//img/@src')
for src in src_list:
res_img = requests.get(src)
file_name = src.rsplit('/', 1)[1].rsplit('.')[0] + '.png'
token_url = f'https://www.jianshu.com/upload_images/token.json?filename={file_name}'
res_token = self.sess.get(token_url)
if res_token.text:
res_token_json = res_token.json()
token = res_token_json.get('token')
key = res_token_json.get('key')
if token and key:
m = MultipartEncoder(
fields={
"file": (file_name, res_img.content),
'token': token,
'key': key,
'x:protocol': 'https'
})
headers_dict = headers_to_dict(upload_head)
headers_dict['Content-Type'] = m.content_type
res_upload_file = requests.post(url=upload_url,
data=m,
headers=headers_dict)
if res_upload_file.text:
r_json = res_upload_file.json()
if r_json.get('error'):
continue
# 图片在文章中本来就不存在
img_url = r_json.get('url')
content = content.replace(src, img_url)
time.sleep(random.random())
return content
