def extract_half_infobox(sideid):
bititle_xpath_template = '//*[@class="basic-info"]/dl[%d]/dt[%%d]' % sideid
bicontent_xpath_template = '//*[@class="basic-info"]/dl[%d]/dd[%%d]' % sideid
counter = 1
while True:
bititle_elements = root.xpath(bititle_xpath_template % counter)
bicontent_elements = root.xpath(bicontent_xpath_template % counter)
if len(bititle_elements) != 1 or len(bicontent_elements) != 1:
# both are zero, we are exiting
if len(bititle_elements) == 0 and len(bicontent_elements) == 0:
break
else:
error = 'extractor2: should exit with (len(bititle)==0 and len(bicontent)==0), but '\
'got (len(bititle)=%d, len(bicontent)=%d)' % (len(bititle_elements), len(bicontent_elements))
raise ValueError(error)
if len(bicontent_elements[0].xpath('.//dl'))>0:
# we should extract expanded values
bicontent_elements = bicontent_elements[0].xpath('.//dd')
remove_tailing_expand_sign=True
else:
remove_tailing_expand_sign=False
bititle = get_inner_text_with_hrefs(bititle_elements[0])
bicontent = get_inner_text_with_hrefs(bicontent_elements[0])
if remove_tailing_expand_sign:
bicontent = bicontent.strip()
if bicontent[-2:] == u'收起':
bicontent = bicontent[:-2]
yield remove_links(cleanup_verb(bititle)), bicontent
counter += 1
def extract_half_infobox(sideid):
bititle_xpath_template = '//*[@class="basic-info"]/dl[%d]/dt[%%d]' % sideid
bicontent_xpath_template = '//*[@class="basic-info"]/dl[%d]/dd[%%d]' % sideid
counter = 1
while True:
bititle_elements = root.xpath(bititle_xpath_template % counter)
bicontent_elements = root.xpath(bicontent_xpath_template % counter)
if len(bititle_elements) != 1 or len(bicontent_elements) != 1:
# both are zero, we are exiting
if len(bititle_elements) == 0 and len(bicontent_elements) == 0:
break
else:
error = 'extractor2: should exit with (len(bititle)==0 and len(bicontent)==0), but '\
'got (len(bititle)=%d, len(bicontent)=%d)' % (len(bititle_elements), len(bicontent_elements))
raise ValueError(error)
if len(bicontent_elements[0].xpath('.//dl')) > 0:
# we should extract expanded values
bicontent_elements = bicontent_elements[0].xpath('.//dd')
remove_tailing_expand_sign = True
else:
remove_tailing_expand_sign = False
bititle = get_inner_text_with_hrefs(bititle_elements[0])
bicontent = get_inner_text_with_hrefs(bicontent_elements[0])
if remove_tailing_expand_sign:
bicontent = bicontent.strip()
if bicontent[-2:] == u'收起':
bicontent = bicontent[:-2]
yield remove_links(cleanup_verb(bititle)), bicontent
counter += 1
def extract_half_infobox(sideid):
bititle_xpath_template = '//*[@id="baseInfoWrapDom"]/div[%d]/div[%%d]/div/span' % sideid
bicontent_xpath_template = '//*[@id="baseInfoWrapDom"]/div[%d]/div[%%d]/div/div' % sideid
bicontent_multiline_xpath_template = '//*[@id="baseInfoWrapDom"]/div[%d]/div[%%d]/div[@class="biOpenItem"]/div[@class="biOpenItemCon"]/div[@class="biOpenContent"]' % sideid
counter = 1
while True:
bititle_elements = root.xpath(bititle_xpath_template % counter)
bicontent_elements = root.xpath(bicontent_xpath_template % counter)
if len(bititle_elements) != 1 or len(bicontent_elements) != 1:
# if both are zero, we are exiting
if len(bititle_elements) == 0 and len(bicontent_elements) == 0:
break
else:
# some bicontent have multi-lines
if len(bititle_elements) == 1 and len(bicontent_elements) > 1:
bicontent_elements_multiline = root.xpath(bicontent_multiline_xpath_template % counter)
if len(bicontent_elements_multiline) != 1:
error = 'extractor1: should find len(bicontent_elements_multiline)==1, but'\
'got %d' % len(bicontent_elements_multiline)
raise ValueError(error)
bicontent_elements = bicontent_elements_multiline
else:
# we are having trouble
error = 'extractor1: should exit with (len(bititle)==0 and len(bicontent)==0), but '\
'got (len(bititle)=%d, len(bicontent)=%d)' % (len(bititle_elements), len(bicontent_elements))
raise ValueError(error)
bititle = get_inner_text_with_hrefs(bititle_elements[0])
bicontent = get_inner_text_with_hrefs(bicontent_elements[0])
yield remove_links(cleanup_verb(bititle)), bicontent
counter += 1
def extract_half_infobox(sideid):
bititle_xpath_template = '//*[@id="baseInfoWrapDom"]/div[%d]/div[%%d]/div/span' % sideid
bicontent_xpath_template = '//*[@id="baseInfoWrapDom"]/div[%d]/div[%%d]/div/div' % sideid
bicontent_multiline_xpath_template = '//*[@id="baseInfoWrapDom"]/div[%d]/div[%%d]/div[@class="biOpenItem"]/div[@class="biOpenItemCon"]/div[@class="biOpenContent"]' % sideid
counter = 1
while True:
bititle_elements = root.xpath(bititle_xpath_template % counter)
bicontent_elements = root.xpath(bicontent_xpath_template % counter)
if len(bititle_elements) != 1 or len(bicontent_elements) != 1:
# if both are zero, we are exiting
if len(bititle_elements) == 0 and len(bicontent_elements) == 0:
break
else:
# some bicontent have multi-lines
if len(bititle_elements
) == 1 and len(bicontent_elements) > 1:
bicontent_elements_multiline = root.xpath(
bicontent_multiline_xpath_template % counter)
if len(bicontent_elements_multiline) != 1:
error = 'extractor1: should find len(bicontent_elements_multiline)==1, but'\
'got %d' % len(bicontent_elements_multiline)
raise ValueError(error)
bicontent_elements = bicontent_elements_multiline
else:
# we are having trouble
error = 'extractor1: should exit with (len(bititle)==0 and len(bicontent)==0), but '\
'got (len(bititle)=%d, len(bicontent)=%d)' % (len(bititle_elements), len(bicontent_elements))
raise ValueError(error)
bititle = get_inner_text_with_hrefs(bititle_elements[0])
bicontent = get_inner_text_with_hrefs(bicontent_elements[0])
yield remove_links(cleanup_verb(bititle)), bicontent
counter += 1
