🎉 add the scarpy folder

Author: Yangzhedi

README.md

@@ -1,14 +1,20 @@
 # pythonSpider
 some python spiders with BeautifulSoup & requests
 
-## [github](github)
-- 爬取关注或粉丝列表 [followXXXList.py](github/github_followXXXList.py)
-- 爬取用户个人信息 [userInfo.py](github/github_userInfo.py)
+##BS4
 
-## [58同城](58tongcheng)
-- 获取所有的二级菜单列表 [urlLists.py](58tongcheng/tc_urlLists.py)
-- 获取每一个url下的具体信息 [itemInfo.py](58tongcheng/tc_itemInfo.py)
+### [github](bs4/github)
+- 爬取关注或粉丝列表 [followXXXList.py](bs4/github/github_followXXXList.py)
+- 爬取用户个人信息 [userInfo.py](bs4/github/github_userInfo.py)
 
-## [豆瓣](douban)
-- 获取单个电影的短评 [comment.py](douban/douban_comment.py)
-- 获取单个电影的所有大图海报 [photosR.py](douban/douban_photosR.py)
+### [58同城](58tongcheng)
+- 获取所有的二级菜单列表 [urlLists.py](bs4/58tongcheng/tc_urlLists.py)
+- 获取每一个url下的具体信息 [itemInfo.py](bs4/58tongcheng/tc_itemInfo.py)
+
+### [豆瓣](douban)
+- 获取单个电影的短评 [comment.py](bs4/douban/douban_comment.py)
+- 获取单个电影的所有大图海报 [photosR.py](bs4/douban/douban_photosR.py)
+
+##scarpy
+
+### [wiki](scarpy/wikiSpider)

58tongcheng/ReadMe.md renamed to bs4/58tongcheng/ReadMe.md

@@ -0,0 +1,14 @@
+# pythonSpider
+some python spiders with BeautifulSoup & requests
+
+## [github](github)
+- 爬取关注或粉丝列表 [followXXXList.py](github/github_followXXXList.py)
+- 爬取用户个人信息 [userInfo.py](github/github_userInfo.py)
+
+## [58同城](58tongcheng)
+- 获取所有的二级菜单列表 [urlLists.py](58tongcheng/tc_urlLists.py)
+- 获取每一个url下的具体信息 [itemInfo.py](58tongcheng/tc_itemInfo.py)
+
+## [豆瓣](douban)
+- 获取单个电影的短评 [comment.py](douban/douban_comment.py)
+- 获取单个电影的所有大图海报 [photosR.py](douban/douban_photosR.py)

58tongcheng/count.py renamed to bs4/58tongcheng/count.py

@@ -0,0 +1,17 @@
+import requests
+import urllib
+from bs4 import BeautifulSoup
+import time
+import string
+
+url = 'https://github.com/Ovilia'
+
+headers = {
+    'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/47.0.2526.80 Safari/537.36 Core/1.47.933.400 QQBrowser/9.4.8699.400',
+}
+data = requests.get(url, headers=headers)
+soup = BeautifulSoup(data.text, 'lxml')
+print soup.prettify()
+langs = soup.select(' ol.pinned-repos-list > li > span.pinned-repo-item-content > p.text-gray.mb-0')
+for i in langs:
+    print i.get_text().replace(' ','').strip('\n')

58tongcheng/main.py renamed to bs4/58tongcheng/main.py

@@ -0,0 +1,4 @@
+[
+{"title": "Main Page"},
+{"title": "Python (programming language)"}
+]

58tongcheng/tc_itemInfo.py renamed to bs4/58tongcheng/tc_itemInfo.py

@@ -0,0 +1,40 @@
+[
+{"title": "Python (programming language)"},
+{"title": "Software developer"},
+{"title": "Guido van Rossum"},
+{"title": "Python Software Foundation"},
+{"title": "Gradual typing"},
+{"title": "Type system"},
+{"title": "Strong and weak typing"},
+{"title": "Duck typing"},
+{"title": "Software design"},
+{"title": "Software release life cycle"},
+{"title": "Type system"},
+{"title": "Reflection (computer programming)"},
+{"title": "Procedural programming"},
+{"title": "Imperative programming"},
+{"title": "Object-oriented programming"},
+{"title": "Main Page"},
+{"title": "Functional programming"},
+{"title": "Integrated Authority File"},
+{"title": "United States Department of Labor"},
+{"title": "TechRepublic"},
+{"title": "Digital object identifier"},
+{"title": "IEEE Computer Society"},
+{"title": "Grail (web browser)"},
+{"title": "Berkeley Software Distribution"},
+{"title": "glob (programming)"},
+{"title": "Belmont, California"},
+{"title": "List of type designers"},
+{"title": "Computer program"},
+{"title": "Data type"},
+{"title": "Type theory"},
+{"title": "Run time (program lifecycle phase)"},
+{"title": "Compile time"},
+{"title": "Type system"},
+{"title": "Strong and weak typing"},
+{"title": "Uniqueness type"},
+{"title": "Lucee"},
+{"title": "ColdFusion Markup Language"},
+{"title": "C Sharp 4.0"}
+]

58tongcheng/tc_urlLists.py renamed to bs4/58tongcheng/tc_urlLists.py

@@ -0,0 +1,11 @@
+# Automatically created by: scrapy startproject
+#
+# For more information about the [deploy] section see:
+# https://scrapyd.readthedocs.org/en/latest/deploy.html
+
+[settings]
+default = wikiSpider.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = wikiSpider

bs4/README.md

@@ -0,0 +1,20 @@
+# -*- coding: utf-8 -*-
+
+# Define here the models for your scraped items
+#
+# See documentation in:
+# http://doc.scrapy.org/en/latest/topics/items.html
+
+
+from scrapy import Item, Field
+
+#
+# class WikispiderItem(scrapy.Item):
+#     # define the fields for your item here like:
+#     # name = scrapy.Field()
+#     pass
+
+class Article(Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    title = Field()

douban/ReadMe.md renamed to bs4/douban/ReadMe.md

@@ -0,0 +1,11 @@
+# -*- coding: utf-8 -*-
+
+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html
+
+
+class WikispiderPipeline(object):
+    def process_item(self, item, spider):
+        return item

douban/douban_comment.py renamed to bs4/douban/douban_comment.py

@@ -0,0 +1,90 @@
+# -*- coding: utf-8 -*-
+
+# Scrapy settings for wikiSpider project
+#
+# For simplicity, this file contains only settings considered important or
+# commonly used. You can find more settings consulting the documentation:
+#
+#     http://doc.scrapy.org/en/latest/topics/settings.html
+#     http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#     http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+
+BOT_NAME = 'wikiSpider'
+
+SPIDER_MODULES = ['wikiSpider.spiders']
+NEWSPIDER_MODULE = 'wikiSpider.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'wikiSpider (+http://www.yourdomain.com)'
+
+# Obey robots.txt rules
+# ROBOTSTXT_OBEY = True
+
+# Configure maximum concurrent requests performed by Scrapy (default: 16)
+#CONCURRENT_REQUESTS = 32
+
+# Configure a delay for requests for the same website (default: 0)
+# See http://scrapy.readthedocs.org/en/latest/topics/settings.html#download-delay
+# See also autothrottle settings and docs
+#DOWNLOAD_DELAY = 3
+# The download delay setting will honor only one of:
+#CONCURRENT_REQUESTS_PER_DOMAIN = 16
+#CONCURRENT_REQUESTS_PER_IP = 16
+
+# Disable cookies (enabled by default)
+#COOKIES_ENABLED = False
+
+# Disable Telnet Console (enabled by default)
+#TELNETCONSOLE_ENABLED = False
+
+# Override the default request headers:
+#DEFAULT_REQUEST_HEADERS = {
+#   'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
+#   'Accept-Language': 'en',
+#}
+
+# Enable or disable spider middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+#SPIDER_MIDDLEWARES = {
+#    'wikiSpider.middlewares.MyCustomSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'wikiSpider.middlewares.MyCustomDownloaderMiddleware': 543,
+#}
+
+# Enable or disable extensions
+# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
+#EXTENSIONS = {
+#    'scrapy.extensions.telnet.TelnetConsole': None,
+#}
+
+# Configure item pipelines
+# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
+#ITEM_PIPELINES = {
+#    'wikiSpider.pipelines.SomePipeline': 300,
+#}
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See http://doc.scrapy.org/en/latest/topics/autothrottle.html
+#AUTOTHROTTLE_ENABLED = True
+# The initial download delay
+#AUTOTHROTTLE_START_DELAY = 5
+# The maximum download delay to be set in case of high latencies
+#AUTOTHROTTLE_MAX_DELAY = 60
+# The average number of requests Scrapy should be sending in parallel to
+# each remote server
+#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
+# Enable showing throttling stats for every response received:
+#AUTOTHROTTLE_DEBUG = False
+
+# Enable and configure HTTP caching (disabled by default)
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
+#HTTPCACHE_ENABLED = True
+#HTTPCACHE_EXPIRATION_SECS = 0
+#HTTPCACHE_DIR = 'httpcache'
+#HTTPCACHE_IGNORE_HTTP_CODES = []
+#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'

douban/douban_img.py renamed to bs4/douban/douban_img.py

@@ -0,0 +1,4 @@
+# This package will contain the spiders of your Scrapy project
+#
+# Please refer to the documentation for information on how to create and manage
+# your spiders.

douban/douban_photosR.py renamed to bs4/douban/douban_photosR.py

@@ -0,0 +1,20 @@
+from scrapy.contrib.spiders import CrawlSpider, Rule
+from wikiSpider.items import Article
+from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor
+from scrapy import log
+
+class ArticleSpider(CrawlSpider):
+	#log.start(logfile='log.txt', loglevel=log.CRITICAL)
+	name="article"
+	allowed_domains = ["en.wikipedia.org"]
+	start_urls = ["http://en.wikipedia.org/wiki/Python_%28programming_language%29"]
+	rules = [
+		Rule(SgmlLinkExtractor(allow=('(/wiki/)((?!:).)*$'),), callback="parse_item", follow=True)
+	]
+
+	def parse_item(self, response):
+		item = Article()
+		title = response.xpath('//h1/text()')[0].extract()
+		print "Title is: "+title
+		item['title'] = title
+		return item

douban/text.txt renamed to bs4/douban/text.txt

@@ -0,0 +1,19 @@
+from scrapy.selector import Selector
+from scrapy import Spider
+from wikiSpider.items import Article
+
+class ArticleSpider(Spider):
+    #log.start(logfile='log.txt', loglevel=log.CRITICAL)
+	name="noarticle"
+	allowed_domains = ["en.wikipedia.org"]
+	start_urls = [
+        "http://en.wikipedia.org/wiki/Main_Page",
+        "http://en.wikipedia.org/wiki/Python_%28programming_language%29"
+        ]
+
+	def parse(self, response):
+		item = Article()
+		title = response.xpath('//*[@id="n-mainpage-description"]/a/text()')[0].extract()
+		print "Title is: "+title
+		item['title'] = title
+		return item