[common] Add new parameters for _download_webpage

[youtube-dl] / youtube_dl / extractor / common.py

diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
index f0489ede4759d4ed4e1db3448acf05208e56e2e8..b633ea9b92a03be0064ee096cc5fdbe18997e8e7 100644 (file)
--- a/youtube_dl/extractor/common.py
+++ b/youtube_dl/extractor/common.py
@@ -13,6 +13,7 @@ import time
 import xml.etree.ElementTree
 
 from ..compat import (
+    compat_cookiejar,
     compat_http_client,
     compat_urllib_error,
     compat_urllib_parse_urlparse,
@@ -296,9 +297,11 @@ class InfoExtractor(object):
         content = self._webpage_read_content(urlh, url_or_request, video_id, note, errnote, fatal)
         return (content, urlh)
 
-    def _webpage_read_content(self, urlh, url_or_request, video_id, note=None, errnote=None, fatal=True):
+    def _webpage_read_content(self, urlh, url_or_request, video_id, note=None, errnote=None, fatal=True, prefix=None):
         content_type = urlh.headers.get('Content-Type', '')
         webpage_bytes = urlh.read()
+        if prefix is not None:
+            webpage_bytes = prefix + webpage_bytes
         m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type)
         if m:
             encoding = m.group(1)
@@ -357,9 +360,19 @@ class InfoExtractor(object):
 
         return content
 
-    def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True):
+    def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5):
         """ Returns the data of the page as a string """
-        res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal)
+        success = False
+        try_count = 0
+        while success is False:
+            try:
+                res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal)
+                success = True
+            except compat_http_client.IncompleteRead as e:
+                try_count += 1
+                if try_count >= tries:
+                    raise e
+                self._sleep(timeout, video_id)
         if res is False:
             return res
         else:
@@ -478,7 +491,7 @@ class InfoExtractor(object):
             raise RegexNotFoundError('Unable to extract %s' % _name)
         else:
             self._downloader.report_warning('unable to extract %s; '
-                'please report this issue on http://yt-dl.org/bug' % _name)
+                                            'please report this issue on http://yt-dl.org/bug' % _name)
             return None
 
     def _html_search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0, group=None):
@@ -612,7 +625,7 @@ class InfoExtractor(object):
 
     def _twitter_search_player(self, html):
         return self._html_search_meta('twitter:player', html,
-            'twitter card player')
+                                      'twitter card player')
 
     def _sort_formats(self, formats):
         if not formats:
@@ -815,6 +828,11 @@ class InfoExtractor(object):
                 self._downloader.report_warning(msg)
         return res
 
+    def _set_cookie(self, domain, name, value, expire_time=None):
+        cookie = compat_cookiejar.Cookie(0, name, value, None, None, domain, None,
+            None, '/', True, False, expire_time, '', None, None, None)
+        self._downloader.cookiejar.set_cookie(cookie)
+
 
 class SearchInfoExtractor(InfoExtractor):
     """