Merge pull request #4 from iawia002/weibo

fix m.weibo.cn

Author: iawia002

lulu/config.py

@@ -113,3 +113,11 @@
     'Accept-Language': 'en-US,en;q=0.8',
     'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64; rv:51.0) Gecko/20100101 Firefox/51.0',  # noqa
 }
+
+FAKE_HEADERS_MOBILE = {
+    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',  # noqa
+    'Accept-Charset': 'UTF-8,*;q=0.5',
+    'Accept-Encoding': 'gzip,deflate,sdch',
+    'Accept-Language': 'en-US,en;q=0.8',
+    'User-Agent': 'Mozilla/5.0 (Linux; Android 4.4.2; Nexus 4 Build/KOT49H) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/34.0.1847.114 Mobile Safari/537.36',  # noqa
+}

lulu/extractors/miaopai.py

@@ -1,24 +1,29 @@
 #!/usr/bin/env python
 
-__all__ = ['miaopai_download']
+import re
+import json
+
+from lulu import config
+from lulu.common import (
+    match1,
+    url_info,
+    url_size,
+    print_info,
+    get_content,
+    download_urls,
+    playlist_not_supported,
+)
 
-from ..common import *
-import urllib.error
-import urllib.parse
+__all__ = ['miaopai_download']
+site_info = 'miaopai'
 
-fake_headers_mobile = {
-    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
-    'Accept-Charset': 'UTF-8,*;q=0.5',
-    'Accept-Encoding': 'gzip,deflate,sdch',
-    'Accept-Language': 'en-US,en;q=0.8',
-    'User-Agent': 'Mozilla/5.0 (Linux; Android 4.4.2; Nexus 4 Build/KOT49H) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/34.0.1847.114 Mobile Safari/537.36'
-}
 
-def miaopai_download_by_fid(fid, output_dir = '.', merge = False, info_only = False, **kwargs):
-    '''Source: Android mobile'''
+def miaopai_download_by_fid(
+    fid, output_dir='.', merge=False, info_only=False, **kwargs
+):
     page_url = 'http://video.weibo.com/show?fid=' + fid + '&type=mp4'
 
-    mobile_page = get_content(page_url, headers=fake_headers_mobile)
+    mobile_page = get_content(page_url, headers=config.FAKE_HEADERS_MOBILE)
     url = match1(mobile_page, r'<video id=.*?src=[\'"](.*?)[\'"]\W')
     title = match1(mobile_page, r'<title>((.|\n)+?)</title>')
     if not title:
@@ -27,25 +32,43 @@ def miaopai_download_by_fid(fid, output_dir = '.', merge = False, info_only = Fa
     ext, size = 'mp4', url_info(url)[2]
     print_info(site_info, title, ext, size)
     if not info_only:
-        download_urls([url], title, ext, total_size=None, output_dir=output_dir, merge=merge)
+        download_urls(
+            [url], title, ext, total_size=None, output_dir=output_dir,
+            merge=merge
+        )
 
-#----------------------------------------------------------------------
-def miaopai_download(url, output_dir = '.', merge = False, info_only = False, **kwargs):
+
+def miaopai_download(
+    url, output_dir='.', merge=False, info_only=False, **kwargs
+):
     fid = match1(url, r'\?fid=(\d{4}:\w{32})')
-    if fid is not None:
+    if fid:
         miaopai_download_by_fid(fid, output_dir, merge, info_only)
     elif '/p/230444' in url:
         fid = match1(url, r'/p/230444(\w+)')
         miaopai_download_by_fid('1034:'+fid, output_dir, merge, info_only)
     else:
-        mobile_page = get_content(url, headers = fake_headers_mobile)
-        hit = re.search(r'"page_url"\s*:\s*"([^"]+)"', mobile_page)
-        if not hit:
-            raise Exception('Unknown pattern')
-        else:
-            escaped_url = hit.group(1)
-            miaopai_download(urllib.parse.unquote(escaped_url), output_dir=output_dir, merge=merge, info_only=info_only, **kwargs)
-
-site_info = "miaopai"
+        mobile_page = get_content(url, headers=config.FAKE_HEADERS_MOBILE)
+        match_rule = re.compile(
+            r'var \$render_data = \[(.*?)\]\[0\]',
+            re.DOTALL
+        )
+        video_info = json.loads(match_rule.findall(mobile_page)[0])
+        video_url = video_info['status']['page_info']['media_info'][
+            'stream_url'
+        ]
+        title = video_info['status']['page_info']['content2']
+        video_format = 'mp4'
+        size = url_size(video_url)
+        print_info(
+            site_info=site_info, title=title, type=video_format, size=size
+        )
+        if not info_only:
+            download_urls(
+                urls=[video_url], title=title, ext=video_format,
+                total_size=size, **kwargs
+            )
+
+
 download = miaopai_download
-download_playlist = playlist_not_supported('miaopai')
+download_playlist = playlist_not_supported(site_info)

lulu/version.py

@@ -1,4 +1,4 @@
 #!/usr/bin/env python
 
-__version__ = '0.1.1'
+__version__ = '0.1.2'
 script_name = 'lulu'

tests/main.py tests/download.pytests/main.py renamed to tests/download.py

@@ -8,6 +8,8 @@
     youtube,
     yixia,
     bilibili,
+    douyin,
+    miaopai,
 )
 
 
@@ -46,6 +48,15 @@ def test_bilibili(self):
             'https://www.bilibili.com/video/av13228063/', info_only=True
         )
 
+    def test_douyin(self):
+        douyin.download(
+            'https://www.douyin.com/share/video/6492273288897629454',
+            info_only=True
+        )
+
+    def test_weibo(self):
+        miaopai.download('https://m.weibo.cn/status/FEFq863WF', info_only=True)
+
 
 if __name__ == '__main__':
     unittest.main()

tests/runtests.py

@@ -5,12 +5,13 @@
 
 
 TEST_MODULES = [
-    'tests.main',
+    'tests.download',
 ]
 
 
 def all():
     return unittest.defaultTestLoader.loadTestsFromNames(TEST_MODULES)
 
+
 if __name__ == '__main__':
     unittest.main(defaultTest='all')