Skip to content

Commit 4ee875e

Browse files
committed
修改爬虫模板
1 parent c3269fd commit 4ee875e

3 files changed

Lines changed: 18 additions & 6 deletions

File tree

feapder/templates/air_spider_template.tmpl

Lines changed: 6 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -12,10 +12,14 @@ import feapder
1212

1313
class ${spider_name}(feapder.AirSpider):
1414
def start_requests(self):
15-
yield feapder.Request("https://www.baidu.com")
15+
yield feapder.Request("https://spidertools.cn")
1616

1717
def parse(self, request, response):
18-
print(response)
18+
# 提取网站title
19+
print(response.xpath("//title/text()").extract_first())
20+
# 提取网站描述
21+
print(response.xpath("//meta[@name='description']/@content").extract_first())
22+
print("网站地址: ", response.url)
1923

2024

2125
if __name__ == "__main__":

feapder/templates/batch_spider_template.tmpl

Lines changed: 6 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -24,10 +24,14 @@ class ${spider_name}(feapder.BatchSpider):
2424
)
2525

2626
def start_requests(self, task):
27-
yield feapder.Request("https://www.baidu.com")
27+
yield feapder.Request("https://spidertools.cn")
2828

2929
def parse(self, request, response):
30-
print(response)
30+
# 提取网站title
31+
print(response.xpath("//title/text()").extract_first())
32+
# 提取网站描述
33+
print(response.xpath("//meta[@name='description']/@content").extract_first())
34+
print("网站地址: ", response.url)
3135

3236

3337
if __name__ == "__main__":

feapder/templates/spider_template.tmpl

Lines changed: 6 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -17,10 +17,14 @@ class ${spider_name}(feapder.Spider):
1717
)
1818

1919
def start_requests(self):
20-
yield feapder.Request("https://www.baidu.com")
20+
yield feapder.Request("https://spidertools.cn")
2121

2222
def parse(self, request, response):
23-
print(response)
23+
# 提取网站title
24+
print(response.xpath("//title/text()").extract_first())
25+
# 提取网站描述
26+
print(response.xpath("//meta[@name='description']/@content").extract_first())
27+
print("网站地址: ", response.url)
2428

2529

2630
if __name__ == "__main__":

0 commit comments

Comments
 (0)