week1

.gitignore

@@ -102,3 +102,4 @@ venv.bak/
 
 # mypy
 .mypy_cache/
+.DS_Store

week1-challenge-01/read_challenge.py

@@ -0,0 +1,6 @@
+import pandas as pd
+
+def convert(file):
+    df = pd.read_json(file)
+    df1000 = df[:1000]
+    df1000.to_hdf('user_study.h5', key='data')

week1-challenge-02/sql_challenge.py

@@ -0,0 +1,14 @@
+import sqlite3
+import pandas as pd
+
+def count(file, user_id):
+
+    sql_con = sqlite3.connect(file)
+    sql_query = "SELECT * FROM data WHERE user_id == {}".format(user_id)
+    df = pd.read_sql(sql_query, sql_con)
+
+    if len(df)==0:
+        return 0
+    else:
+        sum_minutes = df.minutes.sum()
+        return sum_minutes

week1-challenge-03/github_data.py

@@ -0,0 +1,21 @@
+import requests
+import pandas as pd
+
+def issues(repo):
+    url = "https://api.github.com/repos/{}/issues".format(repo)
+    issues = requests.get(url)
+
+    issues_list = []
+    for issue in issues.json():
+        issues_dict = {'number':issue['number'],
+                    'title':issue['title'],
+                    'user_name':issue['user']['login']}
+        issues_list.append(issues_dict)
+
+    issues_df = pd.DataFrame(issues_list)
+
+    return issues_df
+
+issues("numpy/numpy")
+
+

week1-challenge-04/shiyanlou_user.py

@@ -0,0 +1,20 @@
+import requests
+from lxml import html
+
+
+def user_info(user_id):
+
+    url = "https://www.shiyanlou.com/user/{}/".format(user_id)
+    content = requests.get(url)
+
+    if content.status_code == 200:
+        tree = html.fromstring(content.text)
+        user_name = tree.xpath('//span[@class="username"]/text()')[0]
+        user_level = tree.xpath('//span[@class="user-level"]/text()')[0][1:]
+        join_date = tree.xpath('//span[@class="join-date"]/text()')[0][:10]
+        return user_name, int(user_level), join_date
+    else:
+        user_name, user_level, join_date = (None, None, None)
+        return user_name, user_level, join_date
+
+

week1-challenge-05/shiyanlou/scrapy.cfg

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

week1-challenge-05/shiyanlou/shiyanlou/items.py

@@ -0,0 +1,15 @@
+# -*- coding: utf-8 -*-
+
+# Define here the models for your scraped items
+#
+# See documentation in:
+# https://doc.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class ShiyanlouItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    repo_name = scrapy.Field() # repo 名称
+    update_time = scrapy.Field() # 更新时间

week1-challenge-05/shiyanlou/shiyanlou/middlewares.py

@@ -0,0 +1,103 @@
+# -*- coding: utf-8 -*-
+
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# https://doc.scrapy.org/en/latest/topics/spider-middleware.html
+
+from scrapy import signals
+
+
+class ShiyanlouSpiderMiddleware(object):
+    # Not all methods need to be defined. If a method is not defined,
+    # scrapy acts as if the spider middleware does not modify the
+    # passed objects.
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # This method is used by Scrapy to create your spiders.
+        s = cls()
+        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
+        return s
+
+    def process_spider_input(self, response, spider):
+        # Called for each response that goes through the spider
+        # middleware and into the spider.
+
+        # Should return None or raise an exception.
+        return None
+
+    def process_spider_output(self, response, result, spider):
+        # Called with the results returned from the Spider, after
+        # it has processed the response.
+
+        # Must return an iterable of Request, dict or Item objects.
+        for i in result:
+            yield i
+
+    def process_spider_exception(self, response, exception, spider):
+        # Called when a spider or process_spider_input() method
+        # (from other spider middleware) raises an exception.
+
+        # Should return either None or an iterable of Response, dict
+        # or Item objects.
+        pass
+
+    def process_start_requests(self, start_requests, spider):
+        # Called with the start requests of the spider, and works
+        # similarly to the process_spider_output() method, except
+        # that it doesn’t have a response associated.
+
+        # Must return only requests (not items).
+        for r in start_requests:
+            yield r
+
+    def spider_opened(self, spider):
+        spider.logger.info('Spider opened: %s' % spider.name)
+
+
+class ShiyanlouDownloaderMiddleware(object):
+    # Not all methods need to be defined. If a method is not defined,
+    # scrapy acts as if the downloader middleware does not modify the
+    # passed objects.
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # This method is used by Scrapy to create your spiders.
+        s = cls()
+        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
+        return s
+
+    def process_request(self, request, spider):
+        # Called for each request that goes through the downloader
+        # middleware.
+
+        # Must either:
+        # - return None: continue processing this request
+        # - or return a Response object
+        # - or return a Request object
+        # - or raise IgnoreRequest: process_exception() methods of
+        #   installed downloader middleware will be called
+        return None
+
+    def process_response(self, request, response, spider):
+        # Called with the response returned from the downloader.
+
+        # Must either;
+        # - return a Response object
+        # - return a Request object
+        # - or raise IgnoreRequest
+        return response
+
+    def process_exception(self, request, exception, spider):
+        # Called when a download handler or a process_request()
+        # (from other downloader middleware) raises an exception.
+
+        # Must either:
+        # - return None: continue processing this exception
+        # - return a Response object: stops process_exception() chain
+        # - return a Request object: stops process_exception() chain
+        pass
+
+    def spider_opened(self, spider):
+        spider.logger.info('Spider opened: %s' % spider.name)

week1-challenge-05/shiyanlou/shiyanlou/pipelines.py

@@ -0,0 +1,28 @@
+# -*- coding: utf-8 -*-
+
+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html
+import pandas as pd
+
+class ShiyanlouPipeline(object):
+
+    def process_item(self, item, spider):
+        # 读取 item 数据
+        repo_name = item['repo_name']
+        update_time = item['update_time']
+        # 每条数据组成临时 df_temp
+        df_temp = pd.DataFrame([[repo_name, update_time]], columns=['repo_name', 'update_time'])
+        # 将 df_temp 合并到 df
+        self.df = self.df.append(df_temp, ignore_index=True).sort_values(by=['update_time'], ascending=False)
+
+    #当爬虫启动时
+    def open_spider(self, spider):
+        # 新建一个带列名的空白 df
+        self.df = pd.DataFrame(columns=['repo_name', 'update_time'])
+
+    # 当爬虫关闭时
+    def close_spider(self, spider):
+        # 将 df 存储为 csv 文件
+        pd.DataFrame.to_csv(self.df, "../shiyanlou_repo.csv")

week1-challenge-05/shiyanlou/shiyanlou/settings.py

@@ -0,0 +1,90 @@
+# -*- coding: utf-8 -*-
+
+# Scrapy settings for shiyanlou project
+#
+# For simplicity, this file contains only settings considered important or
+# commonly used. You can find more settings consulting the documentation:
+#
+#     https://doc.scrapy.org/en/latest/topics/settings.html
+#     https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
+#     https://doc.scrapy.org/en/latest/topics/spider-middleware.html
+
+BOT_NAME = 'shiyanlou'
+
+SPIDER_MODULES = ['shiyanlou.spiders']
+NEWSPIDER_MODULE = 'shiyanlou.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'shiyanlou (+http://www.yourdomain.com)'
+
+# Obey robots.txt rules
+ROBOTSTXT_OBEY = False
+
+# Configure maximum concurrent requests performed by Scrapy (default: 16)
+#CONCURRENT_REQUESTS = 32
+
+# Configure a delay for requests for the same website (default: 0)
+# See https://doc.scrapy.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 https://doc.scrapy.org/en/latest/topics/spider-middleware.html
+#SPIDER_MIDDLEWARES = {
+#    'shiyanlou.middlewares.ShiyanlouSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'shiyanlou.middlewares.ShiyanlouDownloaderMiddleware': 543,
+#}
+
+# Enable or disable extensions
+# See https://doc.scrapy.org/en/latest/topics/extensions.html
+#EXTENSIONS = {
+#    'scrapy.extensions.telnet.TelnetConsole': None,
+#}
+
+# Configure item pipelines
+# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html
+ITEM_PIPELINES = {
+   'shiyanlou.pipelines.ShiyanlouPipeline': 300,
+}
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See https://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 https://doc.scrapy.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'

week1-challenge-05/shiyanlou/shiyanlou/spiders/__init__.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.

week1-challenge-05/shiyanlou/shiyanlou/spiders/github.py

@@ -0,0 +1,31 @@
+# -*- coding: utf-8 -*-
+import scrapy
+from shiyanlou.items import ShiyanlouItem
+
+"""
+手动获取下一页爬虫
+"""
+
+class GithubSpider(scrapy.Spider):
+    name = 'github'
+    allowed_domains = ['github.com']
+
+    @property
+    def start_urls(self):
+        url_temp = 'https://github.com/shiyanlou?after={}&tab=repositories'
+        after = [
+            '',
+            'Y3Vyc29yOnYyOpK5MjAxNy0wNi0wNlQxNzozNjoxNSswODowMM4FkpW2',
+            'Y3Vyc29yOnYyOpK5MjAxNS0wMS0yM1QxNDoxODoyMSswODowMM4By2VI',
+            'Y3Vyc29yOnYyOpK5MjAxNC0xMS0xOVQxMDoxMDoyMyswODowMM4BmcsV',
+        ]
+        return (url_temp.format(i) for i in after) # 1-4 页
+
+    def parse(self, response):
+        repos = response.xpath('//li[@itemprop="owns"]')
+        for repo in repos:
+            item = ShiyanlouItem()
+            item['repo_name'] = repo.xpath("./div/h3/a/text()").extract_first().strip()
+            item['update_time'] = repo.xpath("./div/relative-time/@datetime").extract_first()
+
+            yield item

week1-challenge-05/shiyanlou/shiyanlou/spiders/github_next_page.py

@@ -0,0 +1,31 @@
+# -*- coding: utf-8 -*-
+import scrapy
+from shiyanlou.items import ShiyanlouItem
+
+"""
+自动获取下一页爬虫
+"""
+
+class GithubSpider(scrapy.Spider):
+    name = 'github_next_page'
+    allowed_domains = ['github.com']
+
+    @property
+    def start_urls(self):
+        return ('https://github.com/shiyanlou?tab=repositories', )
+
+    def parse(self, response):
+        repos = response.xpath('//li[@itemprop="owns"]')
+        for repo in repos:
+            item = ShiyanlouItem()
+            item['repo_name'] = repo.xpath("./div/h3/a/text()").extract_first().strip()
+            item['update_time'] = repo.xpath('./div/relative-time/@datetime').extract_first()
+
+            yield item
+
+        # 如果 Next 按钮没被禁用，那么表示有下一页
+        spans = response.css('div.pagination span.disabled::text')
+        if len(spans) == 0 or spans[-1].extract() != 'Next':
+            next_url = response.css(
+                'div.pagination a:last-child::attr(href)').extract_first()
+            yield response.follow(next_url, callback=self.parse)