Roxedus/ytdl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

re-format code to pass flake8

Browse Source
This commit is contained in:
sprhawk 2017-12-26 16:38:51 +08:00
parent d2be5bb5af
commit 951043724f
1 changed files with 52 additions and 51 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

103
youtube_dl/extractor/weibo.py
View File

@ -5,7 +5,6 @@ from .common import InfoExtractor
import json import json
import random as rnd import random as rnd
from os import path
import re import re
from ..compat import ( from ..compat import (
@ -17,16 +16,17 @@ from ..utils import (
js_to_json, js_to_json,
) )
class WeiboIE(InfoExtractor): class WeiboIE(InfoExtractor):
_VALID_URL = r'https?://weibo\.com/[0-9]+/(?P<id>[a-zA-Z0-9]+)' _VALID_URL = r'https?://weibo\.com/[0-9]+/(?P<id>[a-zA-Z0-9]+)'
_TEST = { _TEST = {
'url': 'https://weibo.com/6275294458/Fp6RGfbff?type=comment', 'url': 'https://weibo.com/6275294458/Fp6RGfbff?type=comment',
'info_dict': { 'info_dict': {
'id': 'Fp6RGfbff', 'id': 'Fp6RGfbff',
'ext': 'mp4', 'ext': 'mp4',
'title': 'You should have servants to massage you,... 来自Hosico_猫 - 微博', 'title': 'You should have servants to massage you,... 来自Hosico_猫 - 微博',
} }
} }
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
@ -38,32 +38,32 @@ class WeiboIE(InfoExtractor):
'Upgrade-Insecure-Requests': '1', 'Upgrade-Insecure-Requests': '1',
} }
# to get Referer url for genvisitor # to get Referer url for genvisitor
webpage,urlh = self._download_webpage_handle(url, video_id, headers=headers, note="first visit the page") webpage, urlh = self._download_webpage_handle(url, video_id, headers=headers, note="first visit the page")
visitor_url = urlh.geturl() visitor_url = urlh.geturl()
data = urlencode({ data = urlencode({
"cb": "gen_callback", "cb": "gen_callback",
"fp": '{"os":"2","browser":"Gecko57,0,0,0","fonts":"undefined","screenInfo":"1440*900*24","plugins":""}', "fp": '{"os":"2","browser":"Gecko57,0,0,0","fonts":"undefined","screenInfo":"1440*900*24","plugins":""}',
}).encode() }).encode()
headers = { headers = {
'Accept-Encoding': 'gzip, deflate, br', 'Accept-Encoding': 'gzip, deflate, br',
'Accept': '*/*', 'Accept': '*/*',
'Referer': visitor_url, 'Referer': visitor_url,
} }
r_genvisitor = Request( r_genvisitor = Request(
'https://passport.weibo.com/visitor/genvisitor', 'https://passport.weibo.com/visitor/genvisitor',
data = data, data=data,
headers = headers, headers=headers,
method = 'POST' method='POST'
) )
webpage,urlh = self._download_webpage_handle(r_genvisitor, video_id, note="gen visitor") webpage, urlh = self._download_webpage_handle(r_genvisitor, video_id, note="gen visitor")
p = webpage.split("&&")[1] # split "gen_callback && gen_callback(...)" p = webpage.split("&&")[1] # split "gen_callback && gen_callback(...)"
i1 = p.find('{') i1 = p.find('{')
i2 = p.rfind('}') i2 = p.rfind('}')
j = p[i1:i2+1] # get JSON object j = p[i1:i2 + 1] # get JSON object
d = json.loads(j) d = json.loads(j)
tid = d["data"]["tid"] tid = d["data"]["tid"]
cnfd = "%03d" % d["data"]["confidence"] cnfd = "%03d" % d["data"]["confidence"]
@ -76,17 +76,17 @@ class WeiboIE(InfoExtractor):
'cb': 'cross_domain', 'cb': 'cross_domain',
'from': 'weibo', 'from': 'weibo',
'_rand': rnd.random() '_rand': rnd.random()
}) })
gencallback_url = "https://passport.weibo.com/visitor/visitor?" + param gencallback_url = "https://passport.weibo.com/visitor/visitor?" + param
webpage,urlh = self._download_webpage_handle(gencallback_url, video_id, note="gen callback") webpage, urlh = self._download_webpage_handle(gencallback_url, video_id, note="gen callback")
webpage,urlh = self._download_webpage_handle(url, video_id, headers=headers, note="retry to visit the page") webpage, urlh = self._download_webpage_handle(url, video_id, headers=headers, note="retry to visit the page")
# TODO more code goes here, for example ... # TODO more code goes here, for example ...
title = self._html_search_regex(r'<title>(.+?)</title>', webpage, 'title') title = self._html_search_regex(r'<title>(.+?)</title>', webpage, 'title')
video_sources_text = self._search_regex("video-sources=\\\\\"(.+?)\"", webpage, 'video_sources') video_sources_text = self._search_regex("video-sources=\\\\\"(.+?)\"", webpage, 'video_sources')
video_formats = parse.parse_qs(video_sources_text) video_formats = parse.parse_qs(video_sources_text)
formats = [] formats = []
@ -100,28 +100,29 @@ class WeiboIE(InfoExtractor):
'url': vid_url, 'url': vid_url,
'format': 'mp4', 'format': 'mp4',
'height': int(res), 'height': int(res),
}) })
self._sort_formats(formats) self._sort_formats(formats)
uploader = self._og_search_property('nick-name', webpage, 'uploader', default = None) uploader = self._og_search_property('nick-name', webpage, 'uploader', default=None)
return { return {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'uploader': uploader, 'uploader': uploader,
'formats': formats 'formats': formats
# TODO more properties (see youtube_dl/extractor/common.py) # TODO more properties (see youtube_dl/extractor/common.py)
} }
class WeiboMobileIE(InfoExtractor): class WeiboMobileIE(InfoExtractor):
_VALID_URL = r'https?://m.weibo.cn/status/(?P<id>[0-9]+)(\?.+)?' _VALID_URL = r'https?://m.weibo.cn/status/(?P<id>[0-9]+)(\?.+)?'
_TEST = { _TEST = {
'url': 'https://m.weibo.cn/status/4189191225395228?wm=3333_2001&sourcetype=weixin&featurecode=newtitle&from=singlemessage&isappinstalled=0', 'url': 'https://m.weibo.cn/status/4189191225395228?wm=3333_2001&sourcetype=weixin&featurecode=newtitle&from=singlemessage&isappinstalled=0',
'info_dict': { 'info_dict': {
'id': '4189191225395228', 'id': '4189191225395228',
'ext': 'mp4', 'ext': 'mp4',
'title': '午睡当然是要甜甜蜜蜜的啦', 'title': '午睡当然是要甜甜蜜蜜的啦',
'uploader': '柴犬柴犬' 'uploader': '柴犬柴犬'
} }
} }
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
@ -132,22 +133,22 @@ class WeiboMobileIE(InfoExtractor):
'Upgrade-Insecure-Requests': '1', 'Upgrade-Insecure-Requests': '1',
} }
# to get Referer url for genvisitor # to get Referer url for genvisitor
webpage,urlh = self._download_webpage_handle(url, video_id, headers=headers, note="visit the page") webpage, urlh = self._download_webpage_handle(url, video_id, headers=headers, note="visit the page")
js_code = self._search_regex(r'var\s+\$render_data\s*=\s*\[({.*})\]\[0\] \|\| {};', webpage, 'js_code', flags = re.DOTALL) js_code = self._search_regex(r'var\s+\$render_data\s*=\s*\[({.*})\]\[0\] \|\| {};', webpage, 'js_code', flags=re.DOTALL)
weibo_info = self._parse_json(js_code, video_id, transform_source=js_to_json) weibo_info = self._parse_json(js_code, video_id, transform_source=js_to_json)
page_info = weibo_info['status']['page_info'] page_info = weibo_info['status']['page_info']
title = weibo_info['status']['status_title'] title = weibo_info['status']['status_title']
format = { format = {
'url': page_info['media_info']['stream_url'], 'url': page_info['media_info']['stream_url'],
'format': 'mp4', 'format': 'mp4',
} }
formats = [format] formats = [format]
uploader = weibo_info['status']['user']['screen_name'] uploader = weibo_info['status']['user']['screen_name']
return { return {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'uploader': uploader, 'uploader': uploader,
'formats': formats 'formats': formats
# TODO more properties (see youtube_dl/extractor/common.py) # TODO more properties (see youtube_dl/extractor/common.py)
} }