【转载】Scrapy安装及demo测试笔记

Scrapy安装及demo测试笔记

原创 2016年09月01日 16:34:00

• 标签：
• scrapy /
• python

 

Scrapy安装及demo测试笔记

一、环境搭建

1. 安装scrapy：pip install scrapy

2.安装：PyWin32，可以从网上载已编译好的安装包：http://www.lfd.uci.edu/%7Egohlke/pythonlibs/#pywin32

安装完之后会报如下错误

解决办法，把以下两个文件拷贝到C:\Windows\System32目录下

二、创建scrapy工程（在此用网上别人提供的例子）

1.cmd的方式进到某个指定目录（d:/tmp/）下执行：scrapy startproject myscrapy，命令执行完之后，生成的目录结构如下

2.设置items

1. # -*- coding: utf-8 -*-
2. # Define here the models for your scraped items
3. #
4. # See documentation in:
5. # http://doc.scrapy.org/en/latest/topics/items.html
6. import scrapy
7. class MyscrapyItem(scrapy.Item):
8. news_title = scrapy.Field() #南邮新闻标题
9. news_date = scrapy.Field()  #南邮新闻时间
10. news_url = scrapy.Field()   #南邮新闻的详细链接

3.编写 spider

1. # -*- coding: utf-8 -*-
2. import scrapy
3. from myscrapy.items import MyscrapyItem
4. import logging
5. class myscrapySpider(scrapy.Spider):
6. name = "myscrapy"
7. allowed_domains = ["njupt.edu.cn"]
8. start_urls = [
9. "http://news.njupt.edu.cn/s/222/t/1100/p/1/c/6866/i/1/list.htm",
10. ]
11. def parse(self, response):
12. news_page_num = 14
13. page_num = 386
14. if response.status == 200:
15. for i in range(2,page_num+1):
16. for j in range(1,news_page_num+1):
17. item = MyscrapyItem()
18. item['news_url'],item['news_title'],item['news_date'] = response.xpath(
19. "//div[@id='newslist']/table[1]/tr["+str(j)+"]//a/font/text()"
20. "|//div[@id='newslist']/table[1]/tr["+str(j)+"]//td[@class='postTime']/text()"
21. "|//div[@id='newslist']/table[1]/tr["+str(j)+"]//a/@href").extract()
22. yield item
23. next_page_url = "http://news.njupt.edu.cn/s/222/t/1100/p/1/c/6866/i/"+str(i)+"/list.htm"
24. yield scrapy.Request(next_page_url,callback=self.parse_news)
25. def parse_news(self, response):
26. news_page_num = 14
27. if response.status == 200:
28. for j in range(1,news_page_num+1):
29. item = MyscrapyItem()
30. item['news_url'],item['news_title'],item['news_date'] = response.xpath(
31. "//div[@id='newslist']/table[1]/tr["+str(j)+"]//a/font/text()"
32. "|//div[@id='newslist']/table[1]/tr["+str(j)+"]//td[@class='postTime']/text()"
33. "|//div[@id='newslist']/table[1]/tr["+str(j)+"]//a/@href").extract()
34. yield item

4.编写pipelines

1. # -*- coding: utf-8 -*-
2. # Define your item pipelines here
3. #
4. # Don't forget to add your pipeline to the ITEM_PIPELINES setting
5. # See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html
6. import json
7. class MyscrapyPipeline(object):
8. def __init__(self):
9. self.file = open('myscrapy.txt',mode='wb')
10. def process_item(self, item, spider):
11. self.file.write(item['news_title'].encode("GBK"))
12. self.file.write("\n")
13. self.file.write(item['news_date'].encode("GBK"))
14. self.file.write("\n")
15. self.file.write(item['news_url'].encode("GBK"))
16. self.file.write("\n")
17. return item

5.编写settings.py

1. # -*- coding: utf-8 -*-
2. # Scrapy settings for myscrapy project
3. #
4. # For simplicity, this file contains only settings considered important or
5. # commonly used. You can find more settings consulting the documentation:
6. #
7. #     http://doc.scrapy.org/en/latest/topics/settings.html
8. #     http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
9. #     http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
10. BOT_NAME = 'myscrapy'
11. SPIDER_MODULES = ['myscrapy.spiders']
12. NEWSPIDER_MODULE = 'myscrapy.spiders'
13. # Crawl responsibly by identifying yourself (and your website) on the user-agent
14. #USER_AGENT = 'myscrapy (+http://www.yourdomain.com)'
15. # Obey robots.txt rules
16. ROBOTSTXT_OBEY = True
17. # Configure maximum concurrent requests performed by Scrapy (default: 16)
18. #CONCURRENT_REQUESTS = 32
19. # Configure a delay for requests for the same website (default: 0)
20. # See http://scrapy.readthedocs.org/en/latest/topics/settings.html#download-delay
21. # See also autothrottle settings and docs
22. #DOWNLOAD_DELAY = 3
23. # The download delay setting will honor only one of:
24. #CONCURRENT_REQUESTS_PER_DOMAIN = 16
25. #CONCURRENT_REQUESTS_PER_IP = 16
26. # Disable cookies (enabled by default)
27. #COOKIES_ENABLED = False
28. # Disable Telnet Console (enabled by default)
29. #TELNETCONSOLE_ENABLED = False
30. # Override the default request headers:
31. #DEFAULT_REQUEST_HEADERS = {
32. #   'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
33. #   'Accept-Language': 'en',
34. #}
35. # Enable or disable spider middlewares
36. # See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
37. #SPIDER_MIDDLEWARES = {
38. #    'myscrapy.middlewares.MyCustomSpiderMiddleware': 543,
39. #}
40. # Enable or disable downloader middlewares
41. # See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
42. #DOWNLOADER_MIDDLEWARES = {
43. #    'myscrapy.middlewares.MyCustomDownloaderMiddleware': 543,
44. #}
45. # Enable or disable extensions
46. # See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
47. #EXTENSIONS = {
48. #    'scrapy.extensions.telnet.TelnetConsole': None,
49. #}
50. # Configure item pipelines
51. # See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
52. ITEM_PIPELINES = {
53. 'myscrapy.pipelines.MyscrapyPipeline': 1,
54. }
55. # Enable and configure the AutoThrottle extension (disabled by default)
56. # See http://doc.scrapy.org/en/latest/topics/autothrottle.html
57. #AUTOTHROTTLE_ENABLED = True
58. # The initial download delay
59. #AUTOTHROTTLE_START_DELAY = 5
60. # The maximum download delay to be set in case of high latencies
61. #AUTOTHROTTLE_MAX_DELAY = 60
62. # The average number of requests Scrapy should be sending in parallel to
63. # each remote server
64. #AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
65. # Enable showing throttling stats for every response received:
66. #AUTOTHROTTLE_DEBUG = False
67. # Enable and configure HTTP caching (disabled by default)
68. # See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
69. #HTTPCACHE_ENABLED = True
70. #HTTPCACHE_EXPIRATION_SECS = 0
71. #HTTPCACHE_DIR = 'httpcache'
72. #HTTPCACHE_IGNORE_HTTP_CODES = []
73. #HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'

6.进到D:\tmp\myscrapy\myscrapy\spiders启动爬虫并查看结果：scrapy crawl myscrapy

Scrapy安装及demo测试笔记

原创 2016年09月01日 16:34:00

• 标签：
• scrapy /
• python

 

Scrapy安装及demo测试笔记

一、环境搭建

1. 安装scrapy：pip install scrapy

2.安装：PyWin32，可以从网上载已编译好的安装包：http://www.lfd.uci.edu/%7Egohlke/pythonlibs/#pywin32

安装完之后会报如下错误

解决办法，把以下两个文件拷贝到C:\Windows\System32目录下

二、创建scrapy工程（在此用网上别人提供的例子）

1.cmd的方式进到某个指定目录（d:/tmp/）下执行：scrapy startproject myscrapy，命令执行完之后，生成的目录结构如下

2.设置items

1. # -*- coding: utf-8 -*-
2. # Define here the models for your scraped items
3. #
4. # See documentation in:
5. # http://doc.scrapy.org/en/latest/topics/items.html
6. import scrapy
7. class MyscrapyItem(scrapy.Item):
8. news_title = scrapy.Field() #南邮新闻标题
9. news_date = scrapy.Field()  #南邮新闻时间
10. news_url = scrapy.Field()   #南邮新闻的详细链接

3.编写 spider

1. # -*- coding: utf-8 -*-
2. import scrapy
3. from myscrapy.items import MyscrapyItem
4. import logging
5. class myscrapySpider(scrapy.Spider):
6. name = "myscrapy"
7. allowed_domains = ["njupt.edu.cn"]
8. start_urls = [
9. "http://news.njupt.edu.cn/s/222/t/1100/p/1/c/6866/i/1/list.htm",
10. ]
11. def parse(self, response):
12. news_page_num = 14
13. page_num = 386
14. if response.status == 200:
15. for i in range(2,page_num+1):
16. for j in range(1,news_page_num+1):
17. item = MyscrapyItem()
18. item['news_url'],item['news_title'],item['news_date'] = response.xpath(
19. "//div[@id='newslist']/table[1]/tr["+str(j)+"]//a/font/text()"
20. "|//div[@id='newslist']/table[1]/tr["+str(j)+"]//td[@class='postTime']/text()"
21. "|//div[@id='newslist']/table[1]/tr["+str(j)+"]//a/@href").extract()
22. yield item
23. next_page_url = "http://news.njupt.edu.cn/s/222/t/1100/p/1/c/6866/i/"+str(i)+"/list.htm"
24. yield scrapy.Request(next_page_url,callback=self.parse_news)
25. def parse_news(self, response):
26. news_page_num = 14
27. if response.status == 200:
28. for j in range(1,news_page_num+1):
29. item = MyscrapyItem()
30. item['news_url'],item['news_title'],item['news_date'] = response.xpath(
31. "//div[@id='newslist']/table[1]/tr["+str(j)+"]//a/font/text()"
32. "|//div[@id='newslist']/table[1]/tr["+str(j)+"]//td[@class='postTime']/text()"
33. "|//div[@id='newslist']/table[1]/tr["+str(j)+"]//a/@href").extract()
34. yield item

4.编写pipelines

1. # -*- coding: utf-8 -*-
2. # Define your item pipelines here
3. #
4. # Don't forget to add your pipeline to the ITEM_PIPELINES setting
5. # See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html
6. import json
7. class MyscrapyPipeline(object):
8. def __init__(self):
9. self.file = open('myscrapy.txt',mode='wb')
10. def process_item(self, item, spider):
11. self.file.write(item['news_title'].encode("GBK"))
12. self.file.write("\n")
13. self.file.write(item['news_date'].encode("GBK"))
14. self.file.write("\n")
15. self.file.write(item['news_url'].encode("GBK"))
16. self.file.write("\n")
17. return item

5.编写settings.py

1. # -*- coding: utf-8 -*-
2. # Scrapy settings for myscrapy project
3. #
4. # For simplicity, this file contains only settings considered important or
5. # commonly used. You can find more settings consulting the documentation:
6. #
7. #     http://doc.scrapy.org/en/latest/topics/settings.html
8. #     http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
9. #     http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
10. BOT_NAME = 'myscrapy'
11. SPIDER_MODULES = ['myscrapy.spiders']
12. NEWSPIDER_MODULE = 'myscrapy.spiders'
13. # Crawl responsibly by identifying yourself (and your website) on the user-agent
14. #USER_AGENT = 'myscrapy (+http://www.yourdomain.com)'
15. # Obey robots.txt rules
16. ROBOTSTXT_OBEY = True
17. # Configure maximum concurrent requests performed by Scrapy (default: 16)
18. #CONCURRENT_REQUESTS = 32
19. # Configure a delay for requests for the same website (default: 0)
20. # See http://scrapy.readthedocs.org/en/latest/topics/settings.html#download-delay
21. # See also autothrottle settings and docs
22. #DOWNLOAD_DELAY = 3
23. # The download delay setting will honor only one of:
24. #CONCURRENT_REQUESTS_PER_DOMAIN = 16
25. #CONCURRENT_REQUESTS_PER_IP = 16
26. # Disable cookies (enabled by default)
27. #COOKIES_ENABLED = False
28. # Disable Telnet Console (enabled by default)
29. #TELNETCONSOLE_ENABLED = False
30. # Override the default request headers:
31. #DEFAULT_REQUEST_HEADERS = {
32. #   'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
33. #   'Accept-Language': 'en',
34. #}
35. # Enable or disable spider middlewares
36. # See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
37. #SPIDER_MIDDLEWARES = {
38. #    'myscrapy.middlewares.MyCustomSpiderMiddleware': 543,
39. #}
40. # Enable or disable downloader middlewares
41. # See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
42. #DOWNLOADER_MIDDLEWARES = {
43. #    'myscrapy.middlewares.MyCustomDownloaderMiddleware': 543,
44. #}
45. # Enable or disable extensions
46. # See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
47. #EXTENSIONS = {
48. #    'scrapy.extensions.telnet.TelnetConsole': None,
49. #}
50. # Configure item pipelines
51. # See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
52. ITEM_PIPELINES = {
53. 'myscrapy.pipelines.MyscrapyPipeline': 1,
54. }
55. # Enable and configure the AutoThrottle extension (disabled by default)
56. # See http://doc.scrapy.org/en/latest/topics/autothrottle.html
57. #AUTOTHROTTLE_ENABLED = True
58. # The initial download delay
59. #AUTOTHROTTLE_START_DELAY = 5
60. # The maximum download delay to be set in case of high latencies
61. #AUTOTHROTTLE_MAX_DELAY = 60
62. # The average number of requests Scrapy should be sending in parallel to
63. # each remote server
64. #AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
65. # Enable showing throttling stats for every response received:
66. #AUTOTHROTTLE_DEBUG = False
67. # Enable and configure HTTP caching (disabled by default)
68. # See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
69. #HTTPCACHE_ENABLED = True
70. #HTTPCACHE_EXPIRATION_SECS = 0
71. #HTTPCACHE_DIR = 'httpcache'
72. #HTTPCACHE_IGNORE_HTTP_CODES = []
73. #HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'

6.进到D:\tmp\myscrapy\myscrapy\spiders启动爬虫并查看结果：scrapy crawl myscrapy