[FC2Video] Add support, fix #102 ; Add custom header support on all download functions

How could this project survive without customizing Headers?

Now Able to call with

download_urls([video_url], title, ext, size, output_dir, merge=merge,
headers = fake_headers)

and everywhere where you can use Faker.
This commit is contained in:
cnbeining 2015-12-02 20:58:08 -05:00
parent 370b183d81
commit 683a475904
3 changed files with 166 additions and 89 deletions

View File

@ -18,6 +18,7 @@ SITES = {
'douyutv' : 'douyutv',
'ehow' : 'ehow',
'facebook' : 'facebook',
'fc2' : 'fc2video',
'flickr' : 'flickr',
'freesound' : 'freesound',
'fun' : 'funshion',
@ -70,6 +71,7 @@ SITES = {
'vine' : 'vine',
'vk' : 'vk',
'xiami' : 'xiami',
'xiaojiadianvideo' : 'fc2video',
'yinyuetai' : 'yinyuetai',
'miaopai' : 'yixia_miaopai',
'youku' : 'youku',
@ -308,9 +310,11 @@ def get_content(url, headers={}, decoded=True):
return data
def url_size(url, faker = False):
def url_size(url, faker = False, headers = {}):
if faker:
response = request.urlopen(request.Request(url, headers = fake_headers), None)
elif headers:
response = request.urlopen(request.Request(url, headers = headers), None)
else:
response = request.urlopen(url)
@ -323,15 +327,20 @@ def url_size(url, faker = False):
def urls_size(urls):
return sum(map(url_size, urls))
def get_head(url):
def get_head(url, headers = {}):
if headers:
req = request.Request(url, headers = headers)
else:
req = request.Request(url)
req.get_method = lambda : 'HEAD'
res = request.urlopen(req)
return dict(res.headers)
def url_info(url, faker = False):
def url_info(url, faker = False, headers = {}):
if faker:
response = request.urlopen(request.Request(url, headers = fake_headers), None)
elif headers:
response = request.urlopen(request.Request(url, headers = headers), None)
else:
response = request.urlopen(request.Request(url))
@ -376,19 +385,21 @@ def url_info(url, faker = False):
return type, ext, size
def url_locations(urls, faker = False):
def url_locations(urls, faker = False, headers = {}):
locations = []
for url in urls:
if faker:
response = request.urlopen(request.Request(url, headers = fake_headers), None)
elif headers:
response = request.urlopen(request.Request(url, headers = headers), None)
else:
response = request.urlopen(request.Request(url))
locations.append(response.url)
return locations
def url_save(url, filepath, bar, refer = None, is_part = False, faker = False):
file_size = url_size(url, faker = faker)
def url_save(url, filepath, bar, refer = None, is_part = False, faker = False, headers = {}):
file_size = url_size(url, faker = faker, headers = headers)
if os.path.exists(filepath):
if not force and file_size == os.path.getsize(filepath):
@ -423,6 +434,8 @@ def url_save(url, filepath, bar, refer = None, is_part = False, faker = False):
if received < file_size:
if faker:
headers = fake_headers
elif headers:
headers = headers
else:
headers = {}
if received:
@ -465,7 +478,7 @@ def url_save(url, filepath, bar, refer = None, is_part = False, faker = False):
os.remove(filepath) # on Windows rename could fail if destination filepath exists
os.rename(temp_filepath, filepath)
def url_save_chunked(url, filepath, bar, refer = None, is_part = False, faker = False):
def url_save_chunked(url, filepath, bar, refer = None, is_part = False, faker = False, headers = {}):
if os.path.exists(filepath):
if not force:
if not is_part:
@ -498,6 +511,8 @@ def url_save_chunked(url, filepath, bar, refer = None, is_part = False, faker =
if faker:
headers = fake_headers
elif headers:
headers = headers
else:
headers = {}
if received:
@ -634,7 +649,7 @@ def get_output_filename(urls, title, ext, output_dir, merge):
merged_ext = 'ts'
return '%s.%s' % (title, merged_ext)
def download_urls(urls, title, ext, total_size, output_dir='.', refer=None, merge=True, faker=False, **kwargs):
def download_urls(urls, title, ext, total_size, output_dir='.', refer=None, merge=True, faker=False, headers = {}, **kwargs):
assert urls
if json_output:
json_output_.download_urls(urls=urls, title=title, ext=ext, total_size=total_size, refer=refer)
@ -671,7 +686,7 @@ def download_urls(urls, title, ext, total_size, output_dir='.', refer=None, merg
if len(urls) == 1:
url = urls[0]
print('Downloading %s ...' % tr(output_filename))
url_save(url, output_filepath, bar, refer = refer, faker = faker)
url_save(url, output_filepath, bar, refer = refer, faker = faker, headers = headers)
bar.done()
else:
parts = []
@ -682,7 +697,7 @@ def download_urls(urls, title, ext, total_size, output_dir='.', refer=None, merg
parts.append(filepath)
#print 'Downloading %s [%s/%s]...' % (tr(filename), i + 1, len(urls))
bar.update_piece(i + 1)
url_save(url, filepath, bar, refer = refer, is_part = True, faker = faker)
url_save(url, filepath, bar, refer = refer, is_part = True, faker = faker, headers = headers)
bar.done()
if not merge:
@ -751,7 +766,7 @@ def download_urls(urls, title, ext, total_size, output_dir='.', refer=None, merg
print()
def download_urls_chunked(urls, title, ext, total_size, output_dir='.', refer=None, merge=True, faker=False):
def download_urls_chunked(urls, title, ext, total_size, output_dir='.', refer=None, merge=True, faker=False, headers = {}):
assert urls
if dry_run:
print('Real URLs:\n%s\n' % urls)
@ -780,7 +795,7 @@ def download_urls_chunked(urls, title, ext, total_size, output_dir='.', refer=No
print('Downloading %s ...' % tr(filename))
filepath = os.path.join(output_dir, filename)
parts.append(filepath)
url_save_chunked(url, filepath, bar, refer = refer, faker = faker)
url_save_chunked(url, filepath, bar, refer = refer, faker = faker, headers = headers)
bar.done()
if not merge:
@ -808,7 +823,7 @@ def download_urls_chunked(urls, title, ext, total_size, output_dir='.', refer=No
parts.append(filepath)
#print 'Downloading %s [%s/%s]...' % (tr(filename), i + 1, len(urls))
bar.update_piece(i + 1)
url_save_chunked(url, filepath, bar, refer = refer, is_part = True, faker = faker)
url_save_chunked(url, filepath, bar, refer = refer, is_part = True, faker = faker, headers = headers)
bar.done()
if not merge:

View File

@ -14,6 +14,7 @@ from .douban import *
from .douyutv import *
from .ehow import *
from .facebook import *
from .fc2video import *
from .flickr import *
from .freesound import *
from .funshion import *

View File

@ -0,0 +1,61 @@
#!/usr/bin/env python
__all__ = ['fc2video_download']
from ..common import *
from hashlib import md5
from urllib.parse import urlparse
import re
#----------------------------------------------------------------------
def makeMimi(upid):
"""From http://cdn37.atwikiimg.com/sitescript/pub/dksitescript/FC2.site.js
Also com.hps.util.fc2.FC2EncrptUtil.makeMimiLocal
L110"""
strSeed = "gGddgPfeaf_gzyr"
prehash = upid + "_" + strSeed
return md5(prehash.encode('utf-8')).hexdigest()
#----------------------------------------------------------------------
def fc2video_download_by_upid(upid, output_dir = '.', merge = True, info_only = False, **kwargs):
""""""
fake_headers = {
'DNT': '1',
'Accept-Encoding': 'gzip, deflate, sdch',
'Accept-Language': 'en-CA,en;q=0.8,en-US;q=0.6,zh-CN;q=0.4,zh;q=0.2',
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/47.0.2526.58 Safari/537.36',
'Accept': '*/*',
'X-Requested-With': 'ShockwaveFlash/19.0.0.245',
'Connection': 'keep-alive',
}
api_base = 'http://video.fc2.com/ginfo.php?upid={upid}&mimi={mimi}'.format(upid = upid, mimi = makeMimi(upid))
html = get_content(api_base, headers=fake_headers)
video_url = match1(html, r'filepath=(.+)&sec')
video_url = video_url.replace('&mid', '?mid')
title = match1(html, r'&title=(.+)&seek_image')
type, ext, size = url_info(video_url, headers=fake_headers)
print_info(site_info, title, type, size)
if not info_only:
download_urls([video_url], title, ext, size, output_dir, merge=merge, headers = fake_headers)
#----------------------------------------------------------------------
def fc2video_download(url, output_dir = '.', merge = True, info_only = False, **kwargs):
"""wrapper"""
#'http://video.fc2.com/en/content/20151021bTVKnbEw'
#'http://xiaojiadianvideo.asia/content/20151021bTVKnbEw'
#'http://video.fc2.com/ja/content/20151021bTVKnbEw'
#'http://video.fc2.com/tw/content/20151021bTVKnbEw'
hostname = urlparse(url).hostname
if not ('fc2.com' in hostname or 'xiaojiadianvideo.asia' in hostname):
return False
upid = match1(url, r'.+/content/(\w+)')
fc2video_download_by_upid(upid, output_dir, merge, info_only)
site_info = "FC2Video"
download = fc2video_download
download_playlist = playlist_not_supported('fc2video')