zhaoxiangpeng
/
science-spider2
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

cnki:更改v的取值

Browse Source
main
zhaoxiangpeng 3 weeks ago
parent a97423e71f
commit a95f242bd5
1 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File

6
science_article_cnki/science_article_cnki/spiders/cnki_article_crossdb.py
Unescape Escape View File

@ -78,6 +78,7 @@ class CnkiArticleCrossdbSpider(scrapy.Spider):
# ---------------------------------------------- 提取列表文章的逻辑 ---------------------------------------------- # ---------------------------------------------- 提取列表文章的逻辑 ----------------------------------------------
tr_nodes = response.xpath('//div[@id="gridTable"]//table[@class="result-table-list"]/tbody/tr') tr_nodes = response.xpath('//div[@id="gridTable"]//table[@class="result-table-list"]/tbody/tr')
for tr_node in tr_nodes: for tr_node in tr_nodes:
check_v = tr_node.xpath('./td[@class="seq"]/input/@value').get() # 下载导出用的v
article_title = tr_node.xpath('./td[@class="name"]/a//text()').getall() # 文章标题 article_title = tr_node.xpath('./td[@class="name"]/a//text()').getall() # 文章标题
article_title = article_title and ''.join(article_title) article_title = article_title and ''.join(article_title)
article_link = tr_node.xpath('./td[@class="name"]/a/@href').get() # 文章链接（有v值） article_link = tr_node.xpath('./td[@class="name"]/a/@href').get() # 文章链接（有v值）
@ -87,7 +88,7 @@ class CnkiArticleCrossdbSpider(scrapy.Spider):
cited_str = tr_node.xpath('./td[@class="quote"]/span/a/text()').get() # 被引量字符串 cited_str = tr_node.xpath('./td[@class="quote"]/span/a/text()').get() # 被引量字符串
param = tools.url_parse(article_link) param = tools.url_parse(article_link)
v = param.get('v') v = check_v
ti_format = ti2format(article_title) ti_format = ti2format(article_title)
ti_unique = ti2unique_type2(ti=ti_format, so=source_title) ti_unique = ti2unique_type2(ti=ti_format, so=source_title)
@ -131,6 +132,7 @@ class CnkiArticleCrossdbSpider(scrapy.Spider):
# ---------------------------------------------- 提取列表文章的逻辑 ---------------------------------------------- # ---------------------------------------------- 提取列表文章的逻辑 ----------------------------------------------
tr_nodes = response.xpath('//div[@id="gridTable"]//table[@class="result-table-list"]/tbody/tr') tr_nodes = response.xpath('//div[@id="gridTable"]//table[@class="result-table-list"]/tbody/tr')
for tr_node in tr_nodes: for tr_node in tr_nodes:
check_v = tr_node.xpath('./td[@class="seq"]/input/@value').get() # 下载导出用的v
article_title = tr_node.xpath('./td[@class="name"]/a/text()').get() # 文章标题 article_title = tr_node.xpath('./td[@class="name"]/a/text()').get() # 文章标题
article_link = tr_node.xpath('./td[@class="name"]/a/@href').get() # 文章链接（有v值） article_link = tr_node.xpath('./td[@class="name"]/a/@href').get() # 文章链接（有v值）
source_title = tr_node.xpath('./td[@class="source"]/*/a/text()').get() # 出版物名称（刊名） source_title = tr_node.xpath('./td[@class="source"]/*/a/text()').get() # 出版物名称（刊名）
@ -139,7 +141,7 @@ class CnkiArticleCrossdbSpider(scrapy.Spider):
cited_str = tr_node.xpath('./td[@class="quote"]/span/a/text()').get() # 被引量字符串 cited_str = tr_node.xpath('./td[@class="quote"]/span/a/text()').get() # 被引量字符串
param = tools.url_parse(article_link) param = tools.url_parse(article_link)
v = param.get('v') v = check_v
ti_format = ti2format(article_title) ti_format = ti2format(article_title)
ti_unique = ti2unique_type2(ti=ti_format, so=source_title) ti_unique = ti2unique_type2(ti=ti_format, so=source_title)
if third_id: if third_id:

Write Preview
Loading…
Cancel
Save