def add_root_url(parser_params={}):
log.debug('''
添加根url
parser_params : %s
''' % str(parser_params))
search_keyword1 = parser_params['search_keyword1']
search_keyword2 = parser_params['search_keyword2']
search_keyword3 = parser_params['search_keyword3']
remark = parser_params
search_keywords = []
for str_key1 in search_keyword1:
for str_key2 in search_keyword2:
search_keywords.append((str_key1 + str_key2).strip())
else:
if not search_keyword1:
search_keywords = search_keyword2
if not search_keyword2:
search_keywords = search_keyword1
for j in search_keywords:
if not j.strip():
continue
for i in range(0, 91, 10):
url = 'http://www.wangpansou.cn/s.php?q=%s&wp=0&start=%d' % (j, i)
if not base_parser.add_url('VA_urls', SITE_ID, url, remark=remark):
base_parser.update_url('VA_urls', url, Constance.TODO)
def add_root_url(search_keyword1=[], search_keyword2=[], search_keyword3=[]):
log.debug(
'''
添加根url
search_keyword1 = %s
search_keyword2 = %s
search_keyword3 = %s
''' %
(str(search_keyword1), str(search_keyword2), str(search_keyword3)))
remark = {
'search_keyword1': search_keyword1,
'search_keyword2': search_keyword2,
'search_keyword3': search_keyword3
}
search_keywords = search_keyword1 + search_keyword2
for search_keyword in search_keywords:
# 取页数
url = 'http://www.sobaidupan.com/search.asp?r=2&wd=%s&p=0&page=0' % search_keyword
html = tools.get_html_by_urllib(url)
regex = ['分页：1/(.*?)页'] # 测试0页
page_count = tools.get_info(html, regex)
page_count = int(page_count[0]) if page_count else 0
print(page_count)
for page in range(0, page_count):
url = 'http://www.sobaidupan.com/search.asp?r=2&wd=%s&p=0&page=%d' % (
search_keyword, page)
if not base_parser.add_url('VA_urls', SITE_ID, url, remark=remark):
base_parser.update_url('VA_urls', url, Constance.TODO)
def parser_program_url(url_info):
log.debug('处理 \n' + tools.dumps_json(url_info))
root_url = url_info['url']
depth = url_info['depth']
site_id = url_info['site_id']
remark = url_info['remark']
classify = remark['classify']
# 解析
html, request = tools.get_html_by_requests(root_url)
if not html:
base_parser.update_url('PROGRAM_urls', root_url, Constance.EXCEPTION)
return
program_blocks = tools.get_tag(html, 'li', {'class': "list_item"})
for program_block in program_blocks:
program_block = str(program_block)
# 地址
regex = 'r-props="{id: \'(.*?)\''
program_id = tools.get_info(program_block, regex, fetch_one=True)
program_url = 'http://v.qq.com/detail/5/%s.html' % program_id
base_parser.add_url("PROGRAM_urls",
site_id,
program_url,
depth=1,
remark={
'program_id': program_id,
'classify': classify
})
base_parser.update_url("PROGRAM_urls", root_url, Constance.DONE)
def run(self):
while True:
try:
urls = self._collector.get_urls(self._urlCount)
log.debug("取到的url大小 %d"%len(urls))
# 判断是否结束
if self._collector.is_finished():
break
for url in urls:
for parser in self._parsers:
if parser.SITE_ID == url['site_id']:
try:
parser.parser(url)
except Exception as e:
log.error(parser.NAME + " parser -- " + str(e))
print(self._tab_urls)
print(url['url'])
base_parser.update_url(self._tab_urls, url['url'], Constance.EXCEPTION)
break
time.sleep(self._interval)
except Exception as e:
log.debug(e)
def add_root_url(parser_params={}):
log.debug('''
添加根url
parser_params : %s
''' % str(parser_params))
search_keyword1 = parser_params['search_keyword1']
search_keyword2 = parser_params['search_keyword2']
search_keyword3 = parser_params['search_keyword3']
remark = parser_params
search_keywords = []
for str_key1 in search_keyword1:
for str_key2 in search_keyword2:
search_keywords.append((str_key1 + str_key2).strip())
else:
if not search_keyword1:
search_keywords = search_keyword2
if not search_keyword2:
search_keywords = search_keyword1
n = 100
for j in search_keywords:
if not j.strip():
continue
for i in range(1, n + 1):
url = 'http://www.bturls.net/search/%s_ctime_%d.html' % (j, i)
if not base_parser.add_url('VA_urls', SITE_ID, url, remark=remark):
base_parser.update_url('VA_urls', url, Constance.TODO)
def run(self):
while True:
try:
urls = self._collector.get_urls(self._url_count)
log.debug("取到的url条数 %d" % len(urls))
# 判断是否结束
if self._collector.is_finished():
break
for url in urls:
for parser in self._parsers:
if parser.SITE_ID == url['site_id']:
try:
parser.parser(url)
except Exception as e:
log.error('''
-------------- parser error -------------
parer name %s
error %s
table %s
deal url %s
''' % (parser.NAME, str(e), self._tab_urls,
str(url)))
base_parser.update_url(self._tab_urls,
url['url'],
Constance.EXCEPTION)
break
time.sleep(self._interval)
except Exception as e:
log.debug(e)
def add_root_url(parser_params={}):
log.debug('''
添加根url
parser_params : %s
''' % str(parser_params))
search_keyword1 = parser_params['search_keyword1']
search_keyword2 = parser_params['search_keyword2']
search_keyword3 = parser_params['search_keyword3']
remark = parser_params
search_keywords = []
for str_key1 in search_keyword1:
for str_key2 in search_keyword2:
search_keywords.append((str_key1 + str_key2).strip())
else:
if not search_keyword1:
search_keywords = search_keyword2
if not search_keyword2:
search_keywords = search_keyword1
for i in search_keywords:
# print(i)
if not i.strip():
continue
for num in range(0, 760, 10):
link = "https://www.baidu.com/s?wd=%s%s&pn=%d" % (i, ' 视频', num)
# print(link)
link = tools.quote(link, safe='#/:?=&%')
if not base_parser.add_url('VA_urls', SITE_ID, link,
remark=remark):
base_parser.update_url('VA_urls', link, Constance.TODO)
def add_root_url(search_keyword1=[], search_keyword2=[], search_keyword3=[]):
log.debug(
'''
添加根url
search_keyword1 = %s
search_keyword2 = %s
search_keyword3 = %s
''' %
(str(search_keyword1), str(search_keyword2), str(search_keyword3)))
remark = {
'search_keyword1': search_keyword1,
'search_keyword2': search_keyword2,
'search_keyword3': search_keyword3
}
search_keyword = search_keyword1 + search_keyword2
for i in search_keyword:
if not i:
continue
for num in range(0, 760, 10):
link = "https://www.baidu.com/s?wd=%s%s&pn=%d" % (i, ' 视频', num)
link = tools.quote(link, safe='#/:?=&%')
if not base_parser.add_url('VA_urls', SITE_ID, link,
remark=remark):
base_parser.update_url('VA_urls', link, Constance.TODO)
def add_root_url(search_keyword1=[], search_keyword2=[], search_keyword3=[]):
log.debug(
'''
添加根url
search_keyword1 = %s
search_keyword2 = %s
search_keyword3 = %s
''' %
(str(search_keyword1), str(search_keyword2), str(search_keyword3)))
remark = {
'search_keyword1': search_keyword1,
'search_keyword2': search_keyword2,
'search_keyword3': search_keyword3
}
search_keywords = search_keyword1 + search_keyword2
for search_keyword in search_keywords:
if not search_keyword:
continue
# 最多显示10页
for page in range(1, 11):
url = 'http://weixin.sogou.com/weixin?type=2&query=' + search_keyword + '&page=%d&ie=utf8' % page
if not base_parser.add_url('VA_urls', SITE_ID, url, remark=remark):
base_parser.update_url('VA_urls', url, Constance.TODO)
def add_root_url(search_keyword1=[], search_keyword2=[], search_keyword3=[]):
log.debug(
'''
添加根url
search_keyword1 = %s
search_keyword2 = %s
search_keyword3 = %s
''' %
(str(search_keyword1), str(search_keyword2), str(search_keyword3)))
remark = {
'search_keyword1': search_keyword1,
'search_keyword2': search_keyword2,
'search_keyword3': search_keyword3
}
search_keywords = search_keyword1 + search_keyword2
for search_keyword in search_keywords:
# 取页数
url = 'https://movie.douban.com/subject_search?start=0&search_text=%s&cat=1002' % search_keyword
html = tools.get_html_by_urllib(url)
regex = '<div class="paginator">.*<a href.*?>(.*?)</a><span class="next"'
page_count = tools.get_info(html, regex)
page_count = int(page_count[0]) if page_count else 0
print(page_count)
for page in range(0, page_count):
url = 'https://movie.douban.com/subject_search?start=%d&search_text=%s&cat=1002' % (
page * 15, search_keyword)
if not base_parser.add_url('VA_urls', SITE_ID, url, remark=remark):
base_parser.update_url('VA_urls', url, Constance.TODO)
def add_root_url(search_keyword1=[], search_keyword2=[], search_keyword3=[]):
log.debug(
'''
添加根url
search_keyword1 = %s
search_keyword2 = %s
search_keyword3 = %s
''' %
(str(search_keyword1), str(search_keyword2), str(search_keyword3)))
remark = {
'search_keyword1': search_keyword1,
'search_keyword2': search_keyword2,
'search_keyword3': search_keyword3
}
search_keyword = search_keyword1 + search_keyword2
for j in search_keyword:
if not j:
continue
for i in range(0, 91, 10):
url = 'http://www.wangpansou.cn/s.php?q=%s&wp=0&start=%d' % (j, i)
if not base_parser.add_url('VA_urls', SITE_ID, url, remark=remark):
base_parser.update_url('VA_urls', url, Constance.TODO)
def parser(url_info):
url_info['_id'] = str(url_info['_id'])
root_url = url_info['url']
depth = url_info['depth']
site_id = url_info['site_id']
remark = url_info['remark']
html = tools.get_json_by_requests(root_url, headers=headers)
data_info = jsonpath.jsonpath(html, '$..video_info')
for data in data_info:
title = data.get('title')
video_url = data.get('play_url')
img_url = data.get('cover_url')
release_time = stamp_to_date(data.get('upline_time'))
if video_url !='':
info_type = 1
else:
info_type = 2
base_parser.save_info('content_info', site_id=SITE_ID, url=video_url, title=title,site_name=NAME,
content='', release_time=release_time, image_url=img_url,
video_url=video_url, is_out_link=1, download_image=False, is_debug=False,
info_type=info_type)
base_parser.update_url('urls', root_url, Constance.DONE)
def parser(url_info):
url_info['_id'] = str(url_info['_id'])
log.debug('处理 \n' + tools.dumps_json(url_info))
root_url = url_info['url']
depth = url_info['depth']
site_id = url_info['site_id']
remark = url_info['remark']
offset = remark.get('offset')
html = tools.get_html_by_webdirver(root_url)
headers = tools.get_tag(html, 'div', {'class': 'result'}, find_all=True)
if not headers:
base_parser.update_url('BAIDU_NEWS_urls', root_url, Constance.DONE)
for header in headers:
# 查看更多相关新闻
regex = ' <span class="c-info"><a.*?href="(.*?)".*?查看更多相关新闻'
more_news_url = tools.get_info(str(header), regex, fetch_one = True)
if more_news_url:
more_news_url = tools.get_full_url('http://news.baidu.com', more_news_url)
more_news_url = more_news_url.replace('amp;', '')
base_parser.add_url('BAIDU_NEWS_urls', SITE_ID, more_news_url, depth = 1, remark = {'offset':0})
url = header.h3.a['href']
article_extractor = ArticleExtractor(url)
content = title = release_time = author = website_domain =''
content = article_extractor.get_content()
if content:
title = article_extractor.get_title()
release_time = article_extractor.get_release_time()
author = article_extractor.get_author()
website_domain = tools.get_domain(url)
uuid = tools.get_uuid(title, website_domain)
website_name = ''
website_position = None
log.debug('''
uuid %s
title %s
author %s
release_time %s
domain %s
url %s
content %s
'''%(uuid, title, author, release_time, website_domain, url, '...'))
# 入库
if tools.is_have_chinese(content):
is_continue = self_base_parser.add_news_acticle(uuid, title, author, release_time, website_name , website_domain, website_position, url, content)
if not is_continue:
break
else:
# 循环正常结束 该页均正常入库， 继续爬取下页
offset += 50
url = tools.replace_str(root_url, 'pn=\d*', 'pn=%d'%offset)
base_parser.add_url('BAIDU_NEWS_urls', SITE_ID, url, depth = 0, remark = {'offset': offset})
base_parser.update_url('BAIDU_NEWS_urls', root_url, Constance.DONE)
def add_root_url(parser_params={}):
log.debug('''
添加根url
parser_params : %s
''' % str(parser_params))
search_keyword1 = parser_params['search_keyword1']
search_keyword2 = parser_params['search_keyword2']
search_keyword3 = parser_params['search_keyword3']
remark = parser_params
search_keywords = []
for str_key1 in search_keyword1:
for str_key2 in search_keyword2:
search_keywords.append((str_key1 + str_key2).strip())
else:
if not search_keyword1:
search_keywords = search_keyword2
if not search_keyword2:
search_keywords = search_keyword1
for j in search_keywords:
if not j.strip():
continue
for i in range(1, 109):
url = 'https://m.weibo.cn/container/getIndex?type=all&queryVal=%s&luicode=10000011' % j + \
'&lfid=106003type%3D1&' + 'title=%s&containerid=100103type' % j + '%3D1%26q%3D' + '%s&' % j + \
'page=%d' % i
url = tools.quote(url, safe='/:?=&%')
if not base_parser.add_url('VA_urls', SITE_ID, url, remark=remark):
base_parser.update_url('VA_urls', url, Constance.TODO)
def add_root_url(search_keyword1=[], search_keyword2=[], search_keyword3=[]):
log.debug(
'''
添加根url
search_keyword1 = %s
search_keyword2 = %s
search_keyword3 = %s
''' %
(str(search_keyword1), str(search_keyword2), str(search_keyword3)))
remark = {
'search_keyword1': search_keyword1,
'search_keyword2': search_keyword2,
'search_keyword3': search_keyword3
}
search_keyword = search_keyword1 + search_keyword2
n = 100
for j in search_keyword:
if not j:
continue
for i in range(1, n + 1):
url = 'http://www.bturls.net/search/%s_ctime_%d.html' % (j, i)
if not base_parser.add_url('VA_urls', SITE_ID, url, remark=remark):
base_parser.update_url('VA_urls', url, Constance.TODO)
def parser(url_info):
url_info['_id'] = str(url_info['_id'])
log.debug('处理 \n' + tools.dumps_json(url_info))
root_url = url_info['url']
depth = url_info['depth']
site_id = url_info['site_id']
remark = url_info['remark']
html = tools.get_html_by_urllib(root_url)
title = '<tr height="25"><td><a href=".*?" title="(.*?)"'
video_url = ['<tr height="25"><td><a href="(.*?)"']
author = ['<a href="user-.*?.html" target="_blank">(.*?)</a>']
watched_count = ['浏览次数: </span>(.*?) ']
file_size = ['资料大小: </span>(.*?) ']
download_count = ['下载次数: </span>(.*?) ']
titles = tools.get_info(html, title, allow_repeat = True)
video_urls = tools.get_info(html, video_url, allow_repeat = True)
authors = tools.get_info(html, author, allow_repeat = True)
watched_counts = tools.get_info(html, watched_count, allow_repeat = True)
file_sizes = tools.get_info(html, file_size, allow_repeat= True)
download_counts = tools.get_info(html, download_count, allow_repeat = True)
for i in range(len(titles)):
title = titles[i]
title = tools.del_html_tag(title)
video_url = video_urls[i]
video_url = tools.get_full_url('http://www.sobaidupan.com', video_url)
author = authors[i]
watched_count = watched_counts[i]
file_size = file_sizes[i]
download_count = download_counts[i]
log.debug('''
标题： %s
视频地址： %s
作者： %s
观看数 %s
资料大小 %s
下载次数 %s
'''%(title, video_url, author, watched_count, file_size, download_count))
contained_key, contained_key_count = base_parser.get_contained_key(title, '',
remark['search_keyword1'],
remark['search_keyword2'], remark['search_keyword3'])
if not contained_key:
continue
base_parser.add_content_info('VA_content_info', SITE_ID, video_url, title, file_size = file_size,
file_name = title, author = author, watched_count = watched_count,
download_count = download_count, search_type = search_type,
keyword = contained_key, keyword_count = contained_key_count, task_id = remark['task_id'])
base_parser.update_url('VA_urls', root_url, Constance.DONE)
def parser_program(url_info):
url_info['_id'] = str(url_info['_id'])
log.debug('处理 \n' + tools.dumps_json(url_info))
root_url = url_info['url']
depth = url_info['depth']
site_id = url_info['site_id']
remark = url_info['remark']
# 解析
html, request = tools.get_html_by_requests(root_url)
if not html:
base_parser.update_url('PROGRAM_urls', root_url, Constance.EXCEPTION)
return
regex = '<li class="v-item-v5.*?">(.*?)</li>'
video_blocks = tools.get_info(html, regex)
for video_block in video_blocks:
regex = '<a class="u-video" href="(.*?)"'
program_url = tools.get_info(video_block, regex, fetch_one = True)
program_id = program_url[program_url.find('b/') + 2 : program_url.rfind('/')]
program_url = 'http://www.mgtv.com/h/%s.html'%program_id
regex = '<img class="u-image" src="(.*?)"'
image_url = tools.get_info(video_block, regex, fetch_one = True)
regex = 'em class="u-time">(.*?)</em>'
episode = tools.get_info(video_block, regex, fetch_one = True)
regex = '<a class="u-title".*?>(.*?)</a>'
title = tools.get_info(video_block, regex, fetch_one = True)
regex = '<span class="u-desc">(.*?)</span>'
actors_block = tools.get_info(video_block, regex, fetch_one = True)
regex = '<a .*?>(.*?)</a?'
actors = tools.get_info(actors_block, regex)
actors = '/'.join(actors) if actors else '暂无'
detail_html, r = tools.get_html_by_requests(program_url)
regex = '<em class="label">简介.*?<span>(.*?)</span>'
summary = tools.get_info(detail_html, regex, fetch_one = True) if detail_html else ''
log.debug('''
program_url %s
image_url %s
episode %s
title %s
actors %s
summary %s
'''%(program_url, image_url, episode, title, actors, summary))
program_mongo_id = base_parser.add_program_info('PROGRAM_info', site_id, title, program_url, image_url, episode, directors = '', actors = actors, summary = summary, release_time = '')
# 获取集信息url 没月份参数默认是最近月份的数据
episode_detail_url = 'http://pcweb.api.mgtv.com/variety/showlist?collection_id=' + program_id
base_parser.add_url('PROGRAM_urls', SITE_ID, episode_detail_url, depth = 1, remark = {'program_mongo_id' : program_mongo_id, 'program_id' : program_id})
base_parser.update_url('PROGRAM_urls', root_url, Constance.DONE)
def parser(url_info):
url_info['_id'] = str(url_info['_id'])
log.debug('处理 \n' + tools.dumps_json(url_info))
root_url = url_info['url']
depth = url_info['depth']
site_id = url_info['site_id']
# 获取搜索词比配到的url
start = 0
while True:
urls = mg.search_url(query=root_url,
num=50,
start=start,
pause=random.randint(MIN_SLEEP_TIME,
MAX_SLEEP_TIME))
if not urls:
break
for url in urls:
url = url.replace('amp;', '')
article_extractor = ArticleExtractor(url)
content = title = release_time = author = website_domain = ''
content = article_extractor.get_content()
if content:
title = article_extractor.get_title()
release_time = article_extractor.get_release_time()
author = article_extractor.get_author()
website_domain = tools.get_domain(url)
uuid = tools.get_uuid(title, website_domain)
website_name = ''
website_position = 35 # 境外
log.debug('''
uuid %s
title %s
author %s
release_time %s
domain %s
url %s
content %s
''' % (uuid, title, author, release_time, website_domain,
url, '...'))
# 入库
if tools.is_have_chinese(content):
is_continue = self_base_parser.add_news_acticle(
uuid, title, author, release_time, website_name,
website_domain, website_position, url, content)
if not is_continue:
break
else:
# 循环正常结束 该页均正常入库， 继续爬取下页
start += 50
base_parser.update_url('google_news_urls', root_url, Constance.DONE)
def inner_add_url(base_url, url, remark):
html = tools.get_html_by_urllib(base_url)
regex = 'pg.pageCount = (.*?);'
page_count = tools.get_info(html, regex, allow_repeat=True)
page_count = ''.join(page_count)
page_count = round(float(page_count))
page_count = int(page_count)
for i in range(0, page_count+1):
url = url % i
if not base_parser.add_url('GameApp_urls', SITE_ID, url, remark=remark):
base_parser.update_url('GameApp_urls', url, Constance.TODO)
def inner_add_url(url, remark):
html = tools.get_html_by_urllib(url)
regex = '<li><span></span><a href="(.*?)">.*?</a></li>'
infos = tools.get_info(html, regex)
for info in infos:
info = ''.join(info)
type_url = 'http://shouji.baidu.com' + info
type_html = tools.get_html_by_urllib(type_url)
page_count = '<div class="pager">.*">(.*?)</a>.*?<li class="next">'
page_count = tools.get_info(type_html, page_count)
page_count = ''.join(page_count)
if not page_count:
page_count = '1'
page_count = int(page_count)
for page in range(1, page_count + 1):
url = type_url + 'list_%d.html' % page
if not base_parser.add_url(
'GameApp_urls', SITE_ID, url, remark=remark):
base_parser.update_url('GameApp_urls', url, Constance.TODO)
def run(self):
while True:
try:
urls = self._collector.get_urls(self._url_count)
log.debug("取到的url大小 %d" % len(urls))
# 判断是否结束
if self._collector.is_finished():
break
for url in urls:
for parser in self._parsers:
if parser.SITE_ID == url['site_id']:
try:
if url.get('retry_times', 0) > MAX_RETRY_TIMES:
print('超过最大重试数，放弃url = %s' % url['url'])
base_parser.update_url(
self._tab_urls, url['url'],
Constance.EXCEPTION)
else:
parser.parser(url)
# base_parser.update_url(self._tab_urls, url['url'], Constance.DONE)
except Exception as e:
log.error(
'''
-------------- parser error -------------
parer name %s
error %s
deal url %s
table %s
''' %
(parser.NAME, str(e), url, self._tab_urls))
base_parser.update_url(self._tab_urls,
url['url'],
Constance.EXCEPTION)
break
time.sleep(self._interval)
except Exception as e:
log.debug(e)
def parser(url_info):
# url = 'http://user.xiaoyouzb.net/v3/vod/small_recommend?nwtime=1571816563&sign=883f96aee2655d8885e7815de3423df7&type=1&cateId=13&pageNum=0&isFirst=N&_u=edac2c15598946bd9ba7bda78a83489c&version=4.7.0&platform=android&appx=yuntu&apppn=org.fungo.fungolive&enterprise=0&channel=tencent&market=32&os_version=8.0.0&device_model=MIX%25202&device_code=780493075490198&udid=77e2cb72797f20afdcaaa6265872cea9&androidId=220240afd2e0e640&source=android'
root_url = url_info['url']
cname = url_info['remark']["category_name"]
headers = {
"User-Agent": "yuntutv/4.7.0 (Android 8.0.0)",
"Host": "user.xiaoyouzb.net"
}
json_data = tools.get_json_by_requests(root_url, headers=headers)
data_infos = json_data["data"]
for data_info in data_infos:
publishTime = data_info["publishTime"]
release_time = tools.timestamp_to_date(str(publishTime)[:-3])
title = data_info["content"]
content = data_info["content"]
video_url = data_info["videoUrl"]
img_url = data_info["coverUrl"]
base_parser.save_info('content_info', site_id=SITE_ID, url=video_url, title=title, site_name=NAME,
content=content, release_time=release_time, image_url=img_url,
video_url=video_url, is_out_link=1, download_image=False, is_debug=False,
)
base_parser.update_url('urls', root_url, Constance.DONE)
def parser(url_info):
root_url = url_info['url']
para = url_info["remark"]["para_template"]
headers = url_info["remark"]["header_template"]
response = requests.get(root_url, params=para, headers=headers)
time.sleep(2)
json_info = response.json()
cate = url_info["remark"]["cate_name"]
data_jsons = jsonpath(json_info, "$..items..data")
if cate != '':
for data_info in data_jsons:
data_json = json.loads(data_info)
title = jsonpath(data_json, "$..title")[0]
img_str = glom(data_json, "coverUrl")
img_json = json.loads(img_str)
img_url = img_json["L"][0]
content = jsonpath(data_json, "$..summary")[0]
updateTime = jsonpath(data_json, "$..updateTime")[0]
video_str = glom(data_json, "videoUrl")
video_json = json.loads(video_str)
video_url = video_json["source"]["hd"]
release_time = tools.timestamp_to_date(str(updateTime)[:-3])
base_parser.save_info(
'content_info',
site_id=SITE_ID,
url=video_url,
title=title,
site_name=NAME,
content=content,
release_time=release_time,
image_url=img_url,
video_url=video_url,
is_out_link=1,
download_image=False,
is_debug=False,
)
base_parser.update_url('urls', root_url, Constance.DONE)
def add_root_url(parser_params = {}):
log.debug('''
添加根url
parser_params : %s
'''%str(parser_params))
search_keyword1 = parser_params['search_keyword1']
search_keyword2 = parser_params['search_keyword2']
search_keyword3 = parser_params['search_keyword3']
remark = parser_params
search_keywords = []
for str_key1 in search_keyword1:
for str_key2 in search_keyword2:
search_keywords.append((str_key1 + str_key2).strip())
else:
if not search_keyword1:
search_keywords = search_keyword2
if not search_keyword2:
search_keywords = search_keyword1
for search_keyword in search_keywords:
if not search_keyword.strip():
continue
# 取页数
url = 'http://www.sobaidupan.com/search.asp?r=2&wd=%s&p=0&page=0' % search_keyword
html = tools.get_html_by_urllib(url)
regex = ['分页：1/(.*?)页'] # 测试0页
page_count = tools.get_info(html, regex)
page_count = int(page_count[0]) if page_count else 0
print(page_count)
for page in range(0, page_count):
url = 'http://www.sobaidupan.com/search.asp?r=2&wd=%s&p=0&page=%d'%(search_keyword, page)
if not base_parser.add_url('VA_urls', SITE_ID, url, remark=remark):
base_parser.update_url('VA_urls', url, Constance.TODO)
def parser(url_info):
url_info['_id'] = str(url_info['_id'])
log.debug('处理 \n' + tools.dumps_json(url_info))
source_url = url_info['url']
depth = url_info['depth']
website_id = url_info['site_id']
description = url_info['remark']
html = tools.get_html_by_urllib(source_url)
if html == None:
base_parser.update_url('article_urls', source_url, Constance.EXCEPTION)
return
# 判断中英文
regex = '[\u4e00-\u9fa5]+'
chinese_word = tools.get_info(html, regex)
if not chinese_word:
base_parser.update_url('article_urls', source_url, Constance.EXCEPTION)
return
urls = tools.get_urls(html)
fit_url = tools.fit_url(urls, FIT_URLS)
for url in fit_url:
# log.debug('url = ' + url)
base_parser.add_url('article_urls', website_id, url, depth + 1)
# 取当前页的文章信息
# 标题
regexs = '<h1.*?>(.*?)</h1>'
title = tools.get_info(html, regexs)
title = title and title[0] or ''
title = tools.del_html_tag(title)
# 内容
regexs = ['<div id="content">(.*?)<div class="clear"></div>',
'<div class="article">(.*?)<!--文章操作-->',
'<div id="video_area">(.*?)<!--文章操作-->',
'<div class="content">(.*?)<div id="article_edit">'
]
content = tools.get_info(html, regexs)
content = content and content[0] or ''
content = tools.del_html_tag(content)
log.debug('''
depth = %d
url = %s
title = %s
content = %s
'''%(depth+1, source_url, title, content))
if content and title:
base_parser.add_article_info('article_text_info', website_id, source_url, title, content)
# 更新source_url为done
base_parser.update_url('article_urls', source_url, Constance.DONE)
def add_root_url(search_keyword1 = [], search_keyword2 = [], search_keyword3 = []):
log.debug('''
添加根url
search_keyword1 = %s
search_keyword2 = %s
search_keyword3 = %s
'''%(str(search_keyword1), str(search_keyword2), str(search_keyword3)))
remark = {'search_keyword1': search_keyword1, 'search_keyword2': search_keyword2,
'search_keyword3': search_keyword3}
search_keyword = search_keyword1 + search_keyword2
for j in search_keyword:
if not j:
continue
for i in range(1, 109):
url = 'https://m.weibo.cn/container/getIndex?type=all&queryVal=%s&luicode=10000011' % j + \
'&lfid=106003type%3D1&' + 'title=%s&containerid=100103type' % j + '%3D1%26q%3D' + '%s&' % j + \
'page=%d' % i
url = tools.quote(url, safe='/:?=&%')
if not base_parser.add_url('VA_urls', SITE_ID, url, remark=remark):
base_parser.update_url('VA_urls', url, Constance.TODO)
def parser(url_info):
url_info['_id'] = str(url_info['_id'])
root_url = url_info['url']
depth = url_info['depth']
site_id = url_info['site_id']
remark = url_info['remark']
data = tools.get_json_by_requests(root_url)
data_info = data.get("returnData").get('news')
for info in data_info:
# print(info)
url = info['url']
release_time = info['publishDate']
title = info['title']
video_url = jsonpath.jsonpath(info['video'], '$..relativeUrl')[0]
img_url = info['logo']
if video_url != '':
info_type = 1
else:
info_type = 2
base_parser.save_info('content_info',
site_id=SITE_ID,
url=url,
title=title,
site_name=NAME,
content='',
release_time=release_time,
image_url=img_url,
video_url=video_url,
is_out_link=1,
download_image=False,
is_debug=False,
info_type=info_type)
base_parser.update_url('urls', root_url, Constance.DONE)
def parser(url_info):
url_info['_id'] = str(url_info['_id'])
log.debug('处理 \n' + tools.dumps_json(url_info))
source_url = url_info['url']
depth = url_info['depth']
website_id = url_info['site_id']
description = url_info['remark']
html = tools.get_html_by_urllib(source_url)
if html == None:
base_parser.update_url('article_urls', source_url, Constance.EXCEPTION)
return
# 判断中英文
regex = '[\u4e00-\u9fa5]+'
chinese_word = tools.get_info(html, regex)
if not chinese_word:
base_parser.update_url('article_urls', source_url, Constance.EXCEPTION)
return
urls = tools.get_urls(html, STOP_URLS)
urls = tools.fit_url(urls, "cctv.com")
for url in urls:
# log.debug('url = ' + url)
base_parser.add_url('article_urls', website_id, url, depth + 1)
# 取当前页的文章信息
# 标题
regexs = '<h1><!--repaste.title.begin-->(.*?)<!--repaste.title.end-->'
title = tools.get_info(html, regexs)
title = title and title[0] or ''
title = tools.del_html_tag(title)
# 内容
regexs = ['<!--repaste.body.begin-->(.*?)<!--repaste.body.end-->']
content = tools.get_info(html, regexs)
content = content and content[0] or ''
content = tools.del_html_tag(content)
log.debug('''
depth = %d
url = %s
title = %s
content = %s
''' % (depth + 1, source_url, title, content))
if content and title:
base_parser.add_article_info('article_text_info', website_id,
source_url, title, content)
# 更新source_url为done
base_parser.update_url('article_urls', source_url, Constance.DONE)
def parser_episode_info(url_info):
url_info['_id'] = str(url_info['_id'])
log.debug('处理 \n' + tools.dumps_json(url_info))
root_url = url_info['url']
depth = url_info['depth']
site_id = url_info['site_id']
remark = url_info['remark']
program_id = remark['program_id']
program_mongo_id = remark['program_mongo_id']
episode_json = tools.get_json_by_requests(root_url)
if not episode_json:
base_parser.update_url('PROGRAM_urls', root_url, Constance.DONE)
return
code = episode_json.get('code')
if code is not 200:
base_parser.update_url('PROGRAM_urls', root_url, Constance.DONE)
return
episode_data = episode_json.get('data', {})
episode_info = episode_data.get('info', {})
name = episode_info.get('title', '')
url = episode_info.get('url', '')
image_url = episode_info.get('thumb', '')
episode_num = episode_info.get('series', '')
summary = episode_info.get('desc', '')
time_length = episode_info.get('duration', '')
episode_download_url = episode_data.get('stream', [{'url':''}])[0].get('url')
episode_download_url = 'http://disp.titan.mgtv.com' + episode_download_url
episode_download_info = tools.get_json_by_requests(episode_download_url)
if episode_download_info:
episode_download_url = episode_download_info.get('info', '')
else:
episode_download_url = ''
log.debug('''
program_mongo_id %s
name %s
url %s
image_url %s
episode_num %s
summary %s
time_length %s
episode_download_url %s
'''%(program_mongo_id, name, url, image_url, episode_num, summary, time_length, episode_download_url))
base_parser.add_program_episode_info('PROGRAM_EPISODE_info', site_id, program_mongo_id, episode_num = episode_num, time_length = time_length, episode_name = name, download_status = '', download_url = episode_download_url, episode_url = url, summary = summary, image_url = image_url, sto_path = '')
base_parser.update_url('PROGRAM_urls', root_url, Constance.DONE)
def parser_episode_detail_url(url_info):
url_info['_id'] = str(url_info['_id'])
log.debug('处理 \n' + tools.dumps_json(url_info))
root_url = url_info['url']
depth = url_info['depth']
site_id = url_info['site_id']
remark = url_info['remark']
program_id = remark['program_id']
program_mongo_id = remark['program_mongo_id']
episode_json = tools.get_json_by_requests(root_url)
if not episode_json:
base_parser.update_url('PROGRAM_urls', root_url, Constance.DONE)
return
code = episode_json.get('code')
if code is not 200:
base_parser.update_url('PROGRAM_urls', root_url, Constance.DONE)
return
episode_data = episode_json.get('data', {})
# 解析分集详细信息地址
episode_list = episode_data.get('list', [])
for episode in episode_list:
episode_id = episode['video_id']
episode_detail_url = 'http://pcweb.api.mgtv.com/player/video?video_id=' + episode_id
base_parser.add_url('PROGRAM_urls', SITE_ID, episode_detail_url, depth = 2, remark = {'program_mongo_id' : program_mongo_id, 'program_id' : program_id})
# 解析其他年份和月份的url
episode_years = episode_data.get('tab_y', [])
episode_months = episode_data.get('tab_m', [])
for episode_year in episode_years: #
year = episode_year['t']
temp_program_id = episode_year['id']
episode_list_url = 'http://pcweb.api.mgtv.com/variety/showlist?collection_id=%s'%temp_program_id
# 添加url 没月份参数默认是最近月份的数据
base_parser.add_url('PROGRAM_urls', SITE_ID, episode_list_url, depth = 1, remark = {'program_mongo_id' : program_mongo_id, 'program_id' : temp_program_id})
for episode_month in episode_months[1:]: #去掉最近月份的数据
episode_month = episode_month['m']
episode_list_url = 'http://pcweb.api.mgtv.com/variety/showlist?collection_id=%s&month=%s'%(program_id, episode_month)
# 添加url
base_parser.add_url('PROGRAM_urls', SITE_ID, episode_list_url, depth = 1, remark = {'program_mongo_id' : program_mongo_id, 'program_id' : program_id})
base_parser.update_url('PROGRAM_urls', root_url, Constance.DONE)
