end_str = conf['block_end']
sub_content = ''
if special_str in content:
start_index = content.index(special_str)
sub_content = content[start_index + len(special_str):]
end_index = sub_content.index(end_str)
sub_content = sub_content[0:end_index]
#sub_content = re.sub(r'</?\w+[^>]*>',' ', sub_content)
###
end_mark = conf['end_mark']
song_mark = conf['song_mark']
singer_mark = conf['singer_mark']
find_index = 0
sub_content = tools.str_replace(sub_content)
i = 0
while song_mark in sub_content:
#{
song = ''
singer = ''
if 'simple_parse' in conf and conf['simple_parse']:
start_index = sub_content.index(song_mark)
sub_content = sub_content[start_index + len(song_mark):]
end_index = sub_content.index(end_mark)
html = sub_content[0:end_index]
song_singer = callback(html, conf['callback'])
#tools.debug(song_singer, 1)
song = song_singer['song']
def xiami_parse_detail(self, html, module, conf, info_obj, fp_obj, logger):
# {
# tools.debug(html_section)
# tools.debug(info_obj)
# tools.debug(fp_obj, 1)
parser = HTMLParser.HTMLParser()
dp_fp = fp_obj["dp_fp"]
dd_fp = fp_obj["dd_fp"]
url = info_obj["url"]
logger.info("Start parse url for %s, url: %s" % (module, url))
# tools.debug(url)
html = tools.str_replace(html)
detail_data = {
"url": url,
"album": info_obj["album"],
"artist": "",
"language": "",
"company": "",
"publish_time": "",
"album_type": "",
"album_intro": "",
}
start = '<td valign="top"'
end = "</td>"
start_len = len(start)
end_len = len(end)
parse = ["artist", "language", "company", "publish_time", "album_type"]
for tag in parse:
# {
if start not in html:
break
s_index = html.find(start)
html = html[s_index:]
e_index = html.find(end)
sub_html = html[0 : e_index + end_len]
data = tools.strip_html_tag(sub_html)
# tools.debug(data)
detail_data[tag] = data
html = html[e_index + end_len :]
# } end for tag
# tools.debug(detail_data, 1)
# album intro
start = '<div id="album_intro"'
end = '<div class="album_intro_toggle'
start_len = len(start)
end_len = len(end)
if start in html:
s_index = html.find(start)
e_index = html.find(end)
sub_html = html[s_index:e_index]
data = tools.strip_html_tag(sub_html)
# {
try:
data = parser.unescape(data)
except (UnicodeDecodeError, UnicodeEncodeError), e:
logger.info("Parse data error. [Exception]: %s" % (e))
# }
detail_data["album_intro"] = data
def xiami_parse_detail(self, html, module, conf, info_obj, fp_obj, logger):
#{
#tools.debug(html_section)
#tools.debug(info_obj)
#tools.debug(fp_obj, 1)
parser = HTMLParser.HTMLParser()
dp_fp = fp_obj['dp_fp']
dd_fp = fp_obj['dd_fp']
url = info_obj['url']
logger.info('Start parse url for %s, url: %s' % (module, url))
#tools.debug(url)
html = tools.str_replace(html)
detail_data = {
'url': url,
'album': info_obj['album'],
'artist': '',
'language': '',
'company': '',
'publish_time': '',
'album_type': '',
'album_intro': '',
}
start = '<td valign="top"'
end = '</td>'
start_len = len(start)
end_len = len(end)
parse = ['artist', 'language', 'company', 'publish_time', 'album_type']
for tag in parse:
#{
if start not in html:
break
s_index = html.find(start)
html = html[s_index:]
e_index = html.find(end)
sub_html = html[0:e_index + end_len]
data = tools.strip_html_tag(sub_html)
#tools.debug(data)
detail_data[tag] = data
html = html[e_index + end_len:]
#} end for tag
#tools.debug(detail_data, 1)
# album intro
start = '<div id="album_intro"'
end = '<div class="album_intro_toggle'
start_len = len(start)
end_len = len(end)
if start in html:
s_index = html.find(start)
e_index = html.find(end)
sub_html = html[s_index:e_index]
data = tools.strip_html_tag(sub_html)
#{
try:
data = parser.unescape(data)
except (UnicodeDecodeError, UnicodeEncodeError), e:
logger.info('Parse data error. [Exception]: %s' % (e))
#}
detail_data['album_intro'] = data
def xiami_parse_url(self, html, module, conf, fp, logger):
# {
logger.info("Start parse url for %s" % module)
start_tag = "<li>"
end_tag = "</li>"
deep_url = "http://www.xiami.com%s"
html = tools.str_replace(html)
while start_tag in html:
# {
start_index = html.find(start_tag)
end_index = html.find(end_tag)
sub_html = html[start_index + len(start_tag) : end_index]
# tools.debug(sub_html, 1)
parse_info = {"album": "", "artist": "", "url": "", "year": ""}
# parse deep page url
url = "#"
u_start = 'href="'
u_end = '"'
if u_start in sub_html:
u_s_index = sub_html.find(u_start)
sub_html = sub_html[u_s_index + len(u_start) :]
u_e_index = sub_html.find(u_end)
url = sub_html[0:u_e_index]
sub_html = sub_html[u_e_index + len(u_end) :]
if "/" == url[0]:
url = deep_url % url
else:
url = "/%s" % url
url = deep_url % url
parse_info["url"] = url
# parse album name, singer and year
parse = [
{"name": "album", "start": '<a class="song"', "end": "</a>"},
{"name": "singer", "start": '<a class="singer"', "end": "</a>"},
{"name": "year", "start": '<p class="year"', "end": "</p>"},
]
for obj in parse:
# {
name = obj["name"]
start = obj["start"]
end = obj["end"]
data = ""
start_len = len(start)
end_len = len(end)
if start in sub_html:
s_index = sub_html.find(start)
sub_html = sub_html[s_index:]
e_index = sub_html.find(end)
tmp_html = sub_html[0 : e_index + end_len]
data = tools.strip_html_tag(tmp_html)
sub_html = sub_html[e_index + end_len :]
parse_info[name] = data
# }
# album singer url year
w_str = "%s\t%s\t%s\t%s\n" % (
parse_info["album"],
parse_info["singer"],
parse_info["url"],
parse_info["year"],
)
# tools.debug(w_str, 1)
try:
fp.write(w_str)
except:
logger.warn("Write data fail for %s." % module)
html = html[end_index + len(end_tag) :]
# } end while
logger.info("parse url is completed for %s." % module)
return 0
def xiami_parse_url(self, html, module, conf, fp, logger):
#{
logger.info('Start parse url for %s' % module)
start_tag = '<li>'
end_tag = '</li>'
deep_url = 'http://www.xiami.com%s'
html = tools.str_replace(html)
while start_tag in html:
#{
start_index = html.find(start_tag)
end_index = html.find(end_tag)
sub_html = html[start_index + len(start_tag):end_index]
#tools.debug(sub_html, 1)
parse_info = {'album': '', 'artist': '', 'url': '', 'year': ''}
# parse deep page url
url = '#'
u_start = 'href="'
u_end = '"'
if u_start in sub_html:
u_s_index = sub_html.find(u_start)
sub_html = sub_html[u_s_index + len(u_start):]
u_e_index = sub_html.find(u_end)
url = sub_html[0:u_e_index]
sub_html = sub_html[u_e_index + len(u_end):]
if '/' == url[0]:
url = deep_url % url
else:
url = '/%s' % url
url = deep_url % url
parse_info['url'] = url
# parse album name, singer and year
parse = [
{
'name': 'album',
'start': '<a class="song"',
'end': '</a>',
},
{
'name': 'singer',
'start': '<a class="singer"',
'end': '</a>',
},
{
'name': 'year',
'start': '<p class="year"',
'end': '</p>',
},
]
for obj in parse:
#{
name = obj['name']
start = obj['start']
end = obj['end']
data = ''
start_len = len(start)
end_len = len(end)
if start in sub_html:
s_index = sub_html.find(start)
sub_html = sub_html[s_index:]
e_index = sub_html.find(end)
tmp_html = sub_html[0:e_index + end_len]
data = tools.strip_html_tag(tmp_html)
sub_html = sub_html[e_index + end_len:]
parse_info[name] = data
#}
# album singer url year
w_str = '%s\t%s\t%s\t%s\n' % (
parse_info['album'], parse_info['singer'], parse_info['url'],
parse_info['year'])
#tools.debug(w_str, 1)
try:
fp.write(w_str)
except:
logger.warn('Write data fail for %s.' % module)
html = html[end_index + len(end_tag):]
#} end while
logger.info('parse url is completed for %s.' % module)
return 0
