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(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, requests = tools.get_html_by_requests(root_url, headers=HEADER)
titles = tools.get_tag(
html, 'div', {'id': tools.re.compile('id_cse_content_item_mid_.')})
for i in range(0, len(titles)):
try:
url = tools.get_tag(titles[i].previous_sibling.previous_sibling,
'a',
find_all=False)
url = url['href']
html2 = tools.get_html_by_urllib(url)
regexs = ['<title>(.+?)</title>']
mark = ''.join(tools.get_info(html2, regexs))
regexs = ['不存在', '取消']
if not tools.get_info(mark, regexs):
title = tools.get_text(
titles[i].previous_sibling.previous_sibling)
title = tools.del_html_tag(title)
info = tools.get_text(titles[i])
file_name = tools.del_html_tag(''.join(
tools.get_info(info, '文件名:(.+?)文')))
file_size = tools.del_html_tag(''.join(
tools.get_info(info, '文件大小:(.+?)分')))
author = tools.del_html_tag(''.join(
tools.get_info(info, '分享者:(.+?)时')))
release_time = ''.join(tools.get_info(info,
'时间:(.+?)下')).replace(
'\n', '')
download_count = tools.del_html_tag(''.join(
tools.get_info(info, '下载次数:(.+?)\.')))
except:
continue
log.debug('''
标题： %s
文件大小：%s
文件名字：%s
作者： %s
原文url： %s
下载数量：%s
日期： %s
''' % (title, file_size, file_name, author, url,
download_count, release_time))
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,
url,
title,
file_size=file_size,
file_name=file_name,
author=author,
release_time=release_time,
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(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, requests = tools.get_html_by_requests(root_url)
titles = tools.get_tag(html, 'h3')
video_infos = tools.get_tag(html, 'dt')
for i in range(0, len(titles)):
title = tools.get_text(titles[i])
title = tools.del_html_tag(title)
try:
url = titles[i].a['href']
except:
continue
url = 'http://www.bturls.net' + url
release_time = video_infos[i].span
release_time = tools.get_text(release_time)
file_size = video_infos[i].span.next_sibling.next_sibling
file_size = tools.get_text(file_size)
watched_count = video_infos[
i].span.next_sibling.next_sibling.next_sibling.next_sibling
watched_count = tools.get_text(watched_count)
regexs = ['t/(.+?)\.']
magnet_link = 'magnet:?xt=urn:btih:' + ''.join(
tools.get_info(url, regexs))
log.debug(
'''
标题： %s
文件大小：%s
原文url： %s
观看数量：%s
磁力链接：%s
日期： %s
''' %
(title, file_size, url, watched_count, magnet_link, release_time))
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,
url,
title,
file_size=file_size,
release_time=release_time,
watched_count=watched_count,
magnet_link=magnet_link,
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(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_webdirver(root_url)
headers = tools.get_tag(html, 'h3', {'class': 't'})
for i in range(0, len(headers)):
title = tools.get_text(headers[i])
title = tools.del_html_tag(title)
if tools.re.compile('的相关视频在线观看_百度视频').findall(title):
continue
try:
ssurl = headers[i].a["href"]
except:
continue
r = tools.requests.head(ssurl)
url = r.headers['Location']
try:
img = headers[i].next_sibling()[0].img['src']
except:
img = ''
try:
release_time = headers[i].next_sibling()[0]
release_time = ''.join(
tools.re.compile('\d\d\d\d年\d+?月\d+?日').findall(
str(release_time)))
if not release_time:
release_time = headers[i].next_sibling()[1]
release_time = ''.join(
tools.re.compile('\d\d\d\d年\d+?月\d+?日').findall(
str(release_time)))
if not release_time:
release_time = headers[i].next_sibling()[2]
release_time = ''.join(
tools.re.compile('\d\d\d\d年\d+?月\d+?日').findall(
str(release_time)))
if not release_time:
release_time = headers[i].next_sibling()[3]
release_time = ''.join(
tools.re.compile('\d\d\d\d年\d+?月\d+?日').findall(
str(release_time)))
release_time = release_time.replace('年', '-').replace('月',
'-').replace(
'日', '')
except:
release_time = ''
content = ''
for content in headers[i].next_sibling():
content = tools.get_tag(content,
'div', {'class': 'c-abstract'},
find_all=False)
if content:
content = tools.get_text(content)
break
else:
content = ''
log.debug('''
标题： %s
内容： %s
原文url：%s
图片url：%s
日期： %s
''' % (title, content, url, img, release_time))
contained_key, contained_key_count = base_parser.get_contained_key(
title, content, remark['search_keyword1'],
remark['search_keyword2'], remark['search_keyword3'])
if not contained_key:
continue
is_video1 = base_parser.is_have_video_by_site(url)
if not is_video1:
is_video2 = base_parser.is_have_video_by_judge(title, content)
if is_video2:
html2 = tools.get_html_by_requests(url)
is_video3 = base_parser.is_have_video_by_common(html2)
if not is_video3:
continue
else:
continue
base_parser.add_content_info('VA_content_info',
SITE_ID,
url=url,
title=title,
content=content,
image_url=img,
release_time=release_time,
search_type=search_type,
keyword=contained_key,
keyword_count=contained_key_count)
base_parser.update_url('VA_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']
headers = {
'User-Agent':
'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.75 Safari/537.36',
'Cookie':
'_T_WM=6f2675cab22ec5e018673192b46dd73b; SUB=_2A251adqIDeRxGeNO7FER8ivPyziIHXVWlebArDV6PUJbkdANLXHjkW2Eu3heWA8h0QMZFxI0_fe7-s2Isw..; SUHB=0HThVFDsKbumHU; SCF=AvoSYQqv89TMIxx4YQUcoIdBp2-sjJbx28qHTTnKAHOymGxToTyDJijAZJl_Nqe3ve0x2U-Yk5poeuVn7bSqyt0.; M_WEIBOCN_PARAMS=featurecode%3D20000180%26oid%3D4060829337409043%26luicode%3D10000011%26lfid%3D106003type%253D1%26fid%3D100103type%253D1%2526q%253D%25E5%25A5%25B3%25E4%25B8%25BB%25E6%2592%25AD%26uicode%3D10000011',
'Host':
'm.weibo.cn',
'Accept':
'application/json, text/plain, */*',
'Accept-Encoding':
'gzip, deflate, sdch, br',
'Accept-Language':
'zh-CN,zh;q=0.8',
'Connection':
'keep-alive',
'X-Requested-With':
'XMLHttpRequest',
'Referer':
'https://m.weibo.cn/p/100103type%3D1%26q%3D%E5%A5%B3%E4%B8%BB%E6%92%AD?type=all&queryVal=%E5%A5%B3%E4%B8%BB%E6%92%AD&luicode=10000011&lfid=106003type%3D1&title=%E5%A5%B3%E4%B8%BB%E6%92%AD'
}
resp = tools.requests.get('%s' % root_url, headers=headers)
infos = resp.json()
try:
cards = infos['cards']
except:
base_parser.update_url('VA_urls', root_url, Constance.DONE)
return
for i in cards:
try:
card_group = i['card_group']
# print(card_group)
# print('****************************')
# print('****************************')
for group in card_group:
if group['mblog']:
mblog = group['mblog']
else:
continue
if not get_video_url(mblog):
continue
url = get_url(mblog)
page_url = get_page_url(mblog)
origin = get_origin(mblog)
content = get_content(mblog)
reposts_count = get_reposts_count(mblog)
comment_count = get_comments_count(mblog)
attitudes_count = get_attitudes_count(mblog)
author = get_author(mblog)
image_url = get_image_url(mblog)
release_time = get_release_time(mblog)
video_url = get_video_url(mblog)
log.debug('''
内容： %s
原文url：%s
作者： %s
来源： %s
视频封面:%s
视频地址:%s
日期： %s
转发数： %s
评论数： %s
点赞数： %s
''' % (content, url, author, origin, image_url,
video_url, release_time, str(reposts_count),
str(comment_count), str(attitudes_count)))
contained_key, contained_key_count = base_parser.get_contained_key(
'', content, remark['search_keyword1'],
remark['search_keyword2'], remark['search_keyword3'])
if not contained_key:
continue
base_parser.add_content_info('VA_content_info',
SITE_ID,
url=video_url,
release_time=release_time,
origin=origin,
title=content,
reposts_count=reposts_count,
comment_count=comment_count,
attitudes_count=attitudes_count,
author=author,
image_url=image_url,
video_url=video_url,
search_type=search_type,
keyword=contained_key,
keyword_count=contained_key_count,
task_id=remark['task_id'])
except:
pass
base_parser.update_url('VA_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']
html = tools.get_html_by_urllib(root_url)
regex = '<tr class="item">(.*?)</tr>'
infos = tools.get_info(html, regex)
for info in infos:
title = ['<a href=".*?" onclick=.*?; class="">(.*?)</a>']
title = tools.get_info(info, title, allow_repeat=True)
title = ''.join(title)
title = tools.del_html_tag(title)
video_url = ['<a href="(.*?)" onclick=.*?; class="">']
video_url = tools.get_info(info, video_url, allow_repeat=True)
video_url = ''.join(video_url)
comment_count = ['<span class="pl">\((\d*?)人评价\)</span>']
comment_count = tools.get_info(info, comment_count, allow_repeat=True)
comment_count = ''.join(comment_count)
comment_count = int(comment_count) if comment_count else 0
release_time = '<p class="pl">(\d{4}-\d{2}-\d{2}).*?</p>'
release_time = tools.get_info(info, release_time, allow_repeat=True)
release_time = ''.join(release_time)
image_url = '<img src="(.*?)" alt=".*?" class=""/>'
image_url = tools.get_info(info, image_url, allow_repeat=True)
image_url = ''.join(image_url)
content = '<p class="pl">(.*?)</p>'
content = tools.get_info(info, content, allow_repeat=True)
content = ''.join(content)
contained_key, contained_key_count = base_parser.get_contained_key(
title, content, remark['search_keyword1'],
remark['search_keyword2'], remark['search_keyword3'])
log.debug('''
标题: %s
内容: %s
评论数 %d
视频地址 %s
图片地址 %s
发布时间 %s
关键字： %s
关键字数：%d
''' % (title, content, comment_count, video_url, image_url,
release_time, contained_key, contained_key_count))
if not contained_key:
continue
base_parser.add_content_info('VA_content_info',
SITE_ID,
url=video_url,
title=title,
content=content,
image_url=image_url,
comment_count=comment_count,
release_time=release_time,
keyword=contained_key,
keyword_count=contained_key_count)
base_parser.update_url('VA_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']
# 解析
html, request = tools.get_html_by_requests(root_url, headers=HEADER)
if not html:
base_parser.update_url('urls', root_url, Constance.EXCEPTION)
return
news_box = tools.get_tag(html, name='div', attrs={'class': "news-box"})[0]
news_list = tools.get_tag(news_box, name='li')
for news in news_list:
try:
# 图片
image = tools.get_tag(news, name='img')[0]
image = tools.get_json_value(image, 'src')
# url
url = tools.get_tag(news, name='h3')[0]
try:
url = tools.get_json_value(url.a, 'href')
except:
url = ''
# 标题
title = tools.get_tag(news, name='h3')[0]
title = tools.get_text(title)
title = tools.del_html_tag(title)
# 内容
content = tools.get_tag(news,
name='p',
attrs={'class': "txt-info"})[0]
content = tools.get_text(content)
content = tools.del_html_tag(content)
# 观看数
watched_count = ''
# 来源
origin = tools.get_tag(news, name='div', attrs={'class': "s-p"})[0]
origin = ''.join(tools.get_info(origin, '<a.*?>(.*?)<'))
# 日期
release_time = tools.get_tag(news,
name='div',
attrs={'class': "s-p"})[0]
release_time = tools.get_json_value(release_time, 't')
release_time = tools.timestamp_to_date(int(release_time))
# 判断是否有视频 根据视频播放图标判断
regex = '<div class="img-box">.*?<i></i>.*?</div>'
play_icon = tools.get_info(news, regex)
except:
continue
contained_key, contained_key_count = base_parser.get_contained_key(
title, content, remark['search_keyword1'],
remark['search_keyword2'], remark['search_keyword3'])
log.debug(
'''
标题： %s
内容： %s
来源： %s
原文url：%s
图片url：%s
观看数： %s
日期： %s
有视频： %d
关键词： %s
关键词数:%s
''' %
(title, content, origin, url, image, watched_count, release_time,
play_icon and True or False, contained_key, contained_key_count))
if not contained_key or not play_icon:
continue
base_parser.add_content_info('VA_content_info',
SITE_ID,
url,
title,
content,
image_url=image,
release_time=release_time,
origin=origin,
watched_count=watched_count,
search_type=SEARCH_TYPE,
keyword=contained_key,
keyword_count=contained_key_count)
base_parser.update_url('VA_urls', root_url, Constance.DONE)
