Skip to content
This repository was archived by the owner on Mar 8, 2023. It is now read-only.

Commit 894c717

Browse files
iawia002iawia002
authored
Merge pull request #12 from iawia002/qq
fix qq.com
2 parents 2a18f0e + dbbc79f commit 894c717

3 files changed

Lines changed: 118 additions & 40 deletions

File tree

‎lulu/extractors/qq.py‎

Lines changed: 101 additions & 39 deletions
Original file line numberDiff line numberDiff line change
@@ -1,18 +1,36 @@
11
#!/usr/bin/env python
22

3+
import re
4+
import json
5+
6+
from lulu.util import log
7+
from lulu.extractors.qie import download as qieDownload
8+
from lulu.extractors.qie_video import download_by_url as qie_video_download
9+
from lulu.common import (
10+
match1,
11+
matchall,
12+
url_info,
13+
print_info,
14+
get_content,
15+
url_locations,
16+
download_urls,
17+
playlist_not_supported,
18+
)
19+
20+
321
__all__ = ['qq_download']
22+
site_info = 'QQ.com'
423

5-
from ..common import *
6-
from ..util.log import *
7-
from .qie import download as qieDownload
8-
from .qie_video import download_by_url as qie_video_download
9-
from urllib.parse import urlparse,parse_qs
1024

11-
def qq_download_by_vid(vid, title, output_dir='.', merge=True, info_only=False):
12-
info_api = 'http://vv.video.qq.com/getinfo?otype=json&appver=3.2.19.333&platform=11&defnpayver=1&vid={}'.format(vid)
25+
def qq_download_by_vid(
26+
vid, title, output_dir='.', merge=True, info_only=False
27+
):
28+
info_api = (
29+
'http://vv.video.qq.com/getinfo?otype=json&appver=3.2.19.333'
30+
'&platform=11&defnpayver=1&vid={}'.format(vid)
31+
)
1332
info = get_content(info_api)
1433
video_json = json.loads(match1(info, r'QZOutputJson=(.*)')[:-1])
15-
1634
fn_pre = video_json['vl']['vi'][0]['lnk']
1735
title = video_json['vl']['vi'][0]['ti']
1836
host = video_json['vl']['vi'][0]['ul']['ui'][0]['url']
@@ -21,23 +39,30 @@ def qq_download_by_vid(vid, title, output_dir='.', merge=True, info_only=False):
2139
if seg_cnt == 0:
2240
seg_cnt = 1
2341

24-
best_quality = streams[-1]['name']
42+
# best_quality = streams[-1]['name']
2543
part_format_id = streams[-1]['id']
2644

27-
part_urls= []
45+
part_urls = []
2846
total_size = 0
2947
for part in range(1, seg_cnt+1):
30-
#if seg_cnt == 1 and video_json['vl']['vi'][0]['vh'] <= 480:
31-
# filename = fn_pre + '.mp4'
32-
#else:
33-
# filename = fn_pre + '.p' + str(part_format_id % 10000) + '.' + str(part) + '.mp4'
34-
filename = fn_pre + '.p' + str(part_format_id % 10000) + '.' + str(part) + '.mp4'
35-
key_api = "http://vv.video.qq.com/getkey?otype=json&platform=11&format={}&vid={}&filename={}&appver=3.2.19.333".format(part_format_id, vid, filename)
48+
filename = '{}.p{}.{}.mp4'.format(
49+
fn_pre, str(part_format_id % 10000), str(part)
50+
)
51+
key_api = (
52+
'http://vv.video.qq.com/getkey?otype=json&platform=11&'
53+
'format={}&vid={}&filename={}&appver=3.2.19.333'.format(
54+
part_format_id, vid, filename
55+
)
56+
)
3657
part_info = get_content(key_api)
3758
key_json = json.loads(match1(part_info, r'QZOutputJson=(.*)')[:-1])
3859
if key_json.get('key') is None:
3960
vkey = video_json['vl']['vi'][0]['fvkey']
40-
url = '{}{}?vkey={}'.format(video_json['vl']['vi'][0]['ul']['ui'][0]['url'], fn_pre + '.mp4', vkey)
61+
url = '{}{}?vkey={}'.format(
62+
video_json['vl']['vi'][0]['ul']['ui'][0]['url'],
63+
fn_pre + '.mp4',
64+
vkey
65+
)
4166
else:
4267
vkey = key_json['key']
4368
url = '{}{}?vkey={}'.format(host, filename, vkey)
@@ -54,11 +79,20 @@ def qq_download_by_vid(vid, title, output_dir='.', merge=True, info_only=False):
5479

5580
print_info(site_info, title, ext, total_size)
5681
if not info_only:
57-
download_urls(part_urls, title, ext, total_size, output_dir=output_dir, merge=merge)
82+
download_urls(
83+
part_urls, title, ext, total_size, output_dir=output_dir,
84+
merge=merge
85+
)
5886

59-
def kg_qq_download_by_shareid(shareid, output_dir='.', info_only=False, caption=False):
87+
88+
def kg_qq_download_by_shareid(
89+
shareid, output_dir='.', info_only=False, caption=False
90+
):
6091
BASE_URL = 'http://cgi.kg.qq.com/fcgi-bin/kg_ugc_getdetail'
61-
params_str = '?dataType=jsonp&jsonp=callback&jsonpCallback=jsopgetsonginfo&v=4&outCharset=utf-8&shareid=' + shareid
92+
params_str = (
93+
'?dataType=jsonp&jsonp=callback&jsonpCallback=jsopgetsonginfo&'
94+
'v=4&outCharset=utf-8&shareid={}'.format(shareid)
95+
)
6296
url = BASE_URL + params_str
6397
content = get_content(url)
6498
json_str = content[len('jsonpcallback('):-1]
@@ -70,7 +104,10 @@ def kg_qq_download_by_shareid(shareid, output_dir='.', info_only=False, caption=
70104
real_url = real_url.replace('\/', '/')
71105

72106
ksong_mid = json_data['data']['ksong_mid']
73-
lyric_url = 'http://cgi.kg.qq.com/fcgi-bin/fcg_lyric?jsonpCallback=jsopgetlrcdata&outCharset=utf-8&ksongmid=' + ksong_mid
107+
lyric_url = (
108+
'http://cgi.kg.qq.com/fcgi-bin/fcg_lyric?jsonpCallback=jsopgetlrcdata&'
109+
'outCharset=utf-8&ksongmid={}'.format(ksong_mid)
110+
)
74111
lyric_data = get_content(lyric_url)
75112
lyric_string = lyric_data[len('jsopgetlrcdata('):-1]
76113
lyric_json = json.loads(lyric_string)
@@ -94,24 +131,35 @@ def kg_qq_download_by_shareid(shareid, output_dir='.', info_only=False, caption=
94131
f.write(line)
95132
f.write('\n')
96133

134+
97135
def qq_download(url, output_dir='.', merge=True, info_only=False, **kwargs):
98-
""""""
99136
if re.match(r'https?://egame.qq.com/live\?anchorid=(\d+)', url):
100137
from . import qq_egame
101-
qq_egame.qq_egame_download(url, output_dir=output_dir, merge=merge, info_only=info_only, **kwargs)
138+
qq_egame.qq_egame_download(
139+
url, output_dir=output_dir, merge=merge, info_only=info_only,
140+
**kwargs
141+
)
102142
return
103143

104144
if 'kg.qq.com' in url or 'kg2.qq.com' in url:
105145
shareid = url.split('?s=')[-1]
106146
caption = kwargs['caption']
107-
kg_qq_download_by_shareid(shareid, output_dir=output_dir, info_only=info_only, caption=caption)
147+
kg_qq_download_by_shareid(
148+
shareid, output_dir=output_dir, info_only=info_only,
149+
caption=caption
150+
)
108151
return
109152

110153
if 'live.qq.com' in url:
111154
if 'live.qq.com/video/v' in url:
112-
qie_video_download(url, output_dir=output_dir, merge=merge, info_only=info_only, **kwargs)
155+
qie_video_download(
156+
url, output_dir=output_dir, merge=merge, info_only=info_only,
157+
**kwargs
158+
)
113159
else:
114-
qieDownload(url, output_dir=output_dir, merge=merge, info_only=info_only)
160+
qieDownload(
161+
url, output_dir=output_dir, merge=merge, info_only=info_only
162+
)
115163
return
116164

117165
if 'mp.weixin.qq.com/s?' in url:
@@ -121,19 +169,21 @@ def qq_download(url, output_dir='.', merge=True, info_only=False, **kwargs):
121169
qq_download_by_vid(vid, vid, output_dir, merge, info_only)
122170
return
123171

124-
#do redirect
172+
# do redirect
125173
if 'v.qq.com/page' in url:
126174
# for URLs like this:
127175
# http://v.qq.com/page/k/9/7/k0194pwgw97.html
128176
new_url = url_locations([url])[0]
129177
if url == new_url:
130-
#redirect in js?
178+
# redirect in js?
131179
content = get_content(url)
132-
url = match1(content,r'window\.location\.href="(.*?)"')
180+
url = match1(content, r'window\.location\.href="(.*?)"')
133181
else:
134182
url = new_url
135183

136-
if 'kuaibao.qq.com' in url or re.match(r'http://daxue.qq.com/content/content/id/\d+', url):
184+
if 'kuaibao.qq.com' in url or re.match(
185+
r'http://daxue.qq.com/content/content/id/\d+', url
186+
):
137187
content = get_content(url)
138188
vid = match1(content, r'vid\s*=\s*"\s*([^"]+)"')
139189
title = match1(content, r'title">([^"]+)</p>')
@@ -144,22 +194,34 @@ def qq_download(url, output_dir='.', merge=True, info_only=False, **kwargs):
144194
title = vid
145195
else:
146196
content = get_content(url)
147-
#vid = parse_qs(urlparse(url).query).get('vid') #for links specified vid like http://v.qq.com/cover/p/ps6mnfqyrfo7es3.html?vid=q0181hpdvo5
148-
rurl = match1(content, r'<link.*?rel\s*=\s*"canonical".*?href\s*="(.+?)".*?>') #https://v.qq.com/x/cover/9hpjiv5fhiyn86u/t0522x58xma.html
149-
vid = ""
197+
# vid = parse_qs(urlparse(url).query).get('vid')
198+
# for links specified vid like
199+
# http://v.qq.com/cover/p/ps6mnfqyrfo7es3.html?vid=q0181hpdvo5
200+
rurl = match1(
201+
content, r'<link.*?rel\s*=\s*"canonical".*?href\s*="(.+?)".*?>'
202+
) # https://v.qq.com/x/cover/9hpjiv5fhiyn86u/t0522x58xma.html
203+
vid = ''
150204
if rurl:
151205
vid = rurl.split('/')[-1].split('.')[0]
152-
vid = vid if vid else url.split('/')[-1].split('.')[0] #https://v.qq.com/x/cover/ps6mnfqyrfo7es3/q0181hpdvo5.html?
153-
vid = vid if vid else match1(content, r'vid"*\s*:\s*"\s*([^"]+)"') #general fallback
206+
if vid == 'undefined':
207+
vid = ''
208+
# https://v.qq.com/x/cover/ps6mnfqyrfo7es3/q0181hpdvo5.html?
209+
vid = vid if vid else url.split('/')[-1].split('.')[0]
210+
# general fallback
211+
vid = vid if vid else match1(content, r'vid"*\s*:\s*"\s*([^"]+)"')
154212
if not vid:
155213
vid = match1(content, r'id"*\s*:\s*"(.+?)"')
156-
title = match1(content,r'<a.*?id\s*=\s*"%s".*?title\s*=\s*"(.+?)".*?>'%vid)
214+
title = match1(
215+
content, r'<a.*?id\s*=\s*"{}".*?title\s*=\s*"(.+?)".*?>'.format(
216+
vid
217+
)
218+
)
157219
title = match1(content, r'title">([^"]+)</p>') if not title else title
158220
title = match1(content, r'"title":"([^"]+)"') if not title else title
159-
title = vid if not title else title #general fallback
221+
title = vid if not title else title # general fallback
160222

161223
qq_download_by_vid(vid, title, output_dir, merge, info_only)
162224

163-
site_info = "QQ.com"
225+
164226
download = qq_download
165-
download_playlist = playlist_not_supported('qq')
227+
download_playlist = playlist_not_supported(site_info)

‎lulu/version.py‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
11
#!/usr/bin/env python
22

3-
__version__ = '0.1.4'
3+
__version__ = '0.1.5'
44
script_name = 'lulu'

‎tests/download.py‎

Lines changed: 16 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -12,6 +12,7 @@
1212
miaopai,
1313
# netease,
1414
youku,
15+
qq,
1516
)
1617

1718

@@ -79,6 +80,21 @@ def test_youku(self):
7980
info_only=True
8081
)
8182

83+
def test_qq(self):
84+
qq.download('https://v.qq.com/x/page/n0528cwq4xr.html', info_only=True)
85+
qq.download(
86+
'https://v.qq.com/x/cover/ps6mnfqyrfo7es3/q0181hpdvo5.html?',
87+
info_only=True
88+
)
89+
qq.download(
90+
'http://v.qq.com/cover/p/ps6mnfqyrfo7es3.html?vid=q0181hpdvo5',
91+
info_only=True
92+
)
93+
qq.download(
94+
'https://v.qq.com/x/cover/9hpjiv5fhiyn86u/t0522x58xma.html',
95+
info_only=True
96+
)
97+
8298

8399
if __name__ == '__main__':
84100
unittest.main()

0 commit comments

Comments
 (0)