Done scraper

This commit is contained in:
Claudio Maggioni (maggicl) 2020-11-04 15:36:32 +01:00
commit 68f7091ecb
12 changed files with 24889 additions and 0 deletions

138
.gitignore vendored Normal file
View file

@ -0,0 +1,138 @@
# Byte-compiled / optimized / DLL files
__pycache__/
*.py[cod]
*$py.class
# C extensions
*.so
# Distribution / packaging
.Python
build/
develop-eggs/
dist/
downloads/
eggs/
.eggs/
lib/
lib64/
parts/
sdist/
var/
wheels/
share/python-wheels/
*.egg-info/
.installed.cfg
*.egg
MANIFEST
# PyInstaller
# Usually these files are written by a python script from a template
# before PyInstaller builds the exe, so as to inject date/other infos into it.
*.manifest
*.spec
# Installer logs
pip-log.txt
pip-delete-this-directory.txt
# Unit test / coverage reports
htmlcov/
.tox/
.nox/
.coverage
.coverage.*
.cache
nosetests.xml
coverage.xml
*.cover
*.py,cover
.hypothesis/
.pytest_cache/
cover/
# Translations
*.mo
*.pot
# Django stuff:
*.log
local_settings.py
db.sqlite3
db.sqlite3-journal
# Flask stuff:
instance/
.webassets-cache
# Scrapy stuff:
.scrapy
# Sphinx documentation
docs/_build/
# PyBuilder
.pybuilder/
target/
# Jupyter Notebook
.ipynb_checkpoints
# IPython
profile_default/
ipython_config.py
# pyenv
# For a library or package, you might want to ignore these files since the code is
# intended to run in multiple environments; otherwise, check them in:
# .python-version
# pipenv
# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
# However, in case of collaboration, if having platform-specific dependencies or dependencies
# having no cross-platform support, pipenv may install dependencies that don't work, or not
# install all needed dependencies.
#Pipfile.lock
# PEP 582; used by e.g. github.com/David-OConnor/pyflow
__pypackages__/
# Celery stuff
celerybeat-schedule
celerybeat.pid
# SageMath parsed files
*.sage.py
# Environments
.env
.venv
env/
venv/
ENV/
env.bak/
venv.bak/
# Spyder project settings
.spyderproject
.spyproject
# Rope project settings
.ropeproject
# mkdocs documentation
/site
# mypy
.mypy_cache/
.dmypy.json
dmypy.json
# Pyre type checker
.pyre/
# pytype static type analyzer
.pytype/
# Cython debug symbols
cython_debug/

0
imgur/__init__.py Normal file
View file

12
imgur/items.py Normal file
View file

@ -0,0 +1,12 @@
# Define here the models for your scraped items
#
# See documentation in:
# https://docs.scrapy.org/en/latest/topics/items.html
import scrapy
class ImgurItem(scrapy.Item):
# define the fields for your item here like:
# name = scrapy.Field()
pass

103
imgur/middlewares.py Normal file
View file

@ -0,0 +1,103 @@
# Define here the models for your spider middleware
#
# See documentation in:
# https://docs.scrapy.org/en/latest/topics/spider-middleware.html
from scrapy import signals
# useful for handling different item types with a single interface
from itemadapter import is_item, ItemAdapter
class ImgurSpiderMiddleware:
# 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, 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 Request 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 doesnt 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 ImgurDownloaderMiddleware:
# 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)

13
imgur/pipelines.py Normal file
View file

@ -0,0 +1,13 @@
# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: https://docs.scrapy.org/en/latest/topics/item-pipeline.html
# useful for handling different item types with a single interface
from itemadapter import ItemAdapter
class ImgurPipeline:
def process_item(self, item, spider):
return item

103
imgur/settings.py Normal file
View file

@ -0,0 +1,103 @@
# Scrapy settings for imgur project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
# https://docs.scrapy.org/en/latest/topics/settings.html
# https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
# https://docs.scrapy.org/en/latest/topics/spider-middleware.html
BOT_NAME = 'imgur'
SPIDER_MODULES = ['imgur.spiders']
NEWSPIDER_MODULE = 'imgur.spiders'
# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64; rv:82.0) Gecko/20100101 Firefox/82.0'
# Obey robots.txt rules
ROBOTSTXT_OBEY = False
SPLASH_URL = 'http://localhost:8050'
DOWNLOADER_MIDDLEWARES = {
'scrapy_splash.SplashCookiesMiddleware': 723,
'scrapy_splash.SplashMiddleware': 725,
'scrapy.downloadermiddlewares.httpcompression.HttpCompressionMiddleware': 810,
}
SPIDER_MIDDLEWARES = {
'scrapy_splash.SplashDeduplicateArgsMiddleware': 100,
}
DUPEFILTER_CLASS = 'scrapy_splash.SplashAwareDupeFilter'
HTTPCACHE_STORAGE = 'scrapy_splash.SplashAwareFSCacheStorage'
# Configure maximum concurrent requests performed by Scrapy (default: 16)
CONCURRENT_REQUESTS = 256
# Configure a delay for requests for the same website (default: 0)
# See https://docs.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://docs.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
# 'imgur.middlewares.ImgurSpiderMiddleware': 543,
#}
# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
# 'imgur.middlewares.ImgurDownloaderMiddleware': 543,
#}
# Enable or disable extensions
# See https://docs.scrapy.org/en/latest/topics/extensions.html
#EXTENSIONS = {
# 'scrapy.extensions.telnet.TelnetConsole': None,
#}
# Configure item pipelines
# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
#ITEM_PIPELINES = {
# 'imgur.pipelines.ImgurPipeline': 300,
#}
# Enable and configure the AutoThrottle extension (disabled by default)
# See https://docs.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://docs.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'

View file

@ -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.

70
imgur/spiders/explore.py Normal file
View file

@ -0,0 +1,70 @@
import scrapy
import re
from scrapy_splash import SplashRequest
import dateparser
class ExploreSpider(scrapy.Spider):
name = "explorescraper"
terms = ['usi', 'eth', 'epfl', 'lugano', 'zurich', 'basel', 'oliveto%20lario', 'homework', 'plagiarism', 'rhb', 'sbb',
'ship', 'frighten', 'fool', 'have', 'inspire', 'heal', 'master', 'terminate', 'amend', 'scratch', 'embark',
'entail', 'execute', 'consolidate', 'cash', 'round', 'isolate', 'warrant', 'signal', 'weaken', 'pin',
'march', 'desire', 'widen', 'level', 'chat', 'board', 'contend', 'invent', 'resource', 'manufacture', 'seal',
'reconsider', 'suck', 'picture', 'crash', 'transport', 'plug', 'assign', 'enquire', 'campaign', 'trap',
'surround', 'debate', 'upgrade', 'decorate', 'confer', 'accumulate', 'profit', 'file', 'inherit', 'disrupt',
'contrast', 'chuck', 'tick', 'plead', 'dip', 'subscribe', 'educate', 'divorce', 'spin', 'row', 'obscure',
'creep', 'interest', 'overlook', 'twist', 'mature', 'blend', 'revise', 'attribute', 'explode', 'dwell',
'drown', 'alleviate', 'strip', 'grade', 'revert', 'value', 'award', 'strive', 'notify', 'remedy', 'accuse',
'instruct', 'spill', 'strain', 'comprehend', 'soften', 'postpone', 'wave', 'bounce', 'stock', 'position',
'insure', 'adhere', 'cling', 'summon','pause','empty','classify']
infinite_scroll_urls = ["https://flickr.com/explore"]
start_urls = ["https://www.flickr.com/photos/tags/train",
"https://www.flickr.com/photos/tags/tree",
"https://www.flickr.com/photos/tags/outside"]
def parse_photo(self, response):
adesc = re.compile("<h2 class=\" meta-field photo-desc \">(.*)<\\/h2>", re.DOTALL)
ad = re.compile("(\\w+\\s*\\d+\\s*,\\s*\\d+)", re.MULTILINE)
photo = {}
photo["author"] = response.css("a.owner-name::text").get().strip(' \n\t')
photo["title"] = response.css("h1::text").get().strip(' \n\t')
photo["description"] = ''.join(adesc.findall(response.text)).strip(' \n\t')
date = response.css("span.date-taken-label::text").get()
date = ad.findall(date)
date = date[0]
photo["date"] = dateparser.parse(date)
if photo["date"] is not None:
photo["date"] = photo["date"].strftime("%Y-%m-%d")
else:
photo["date"] = ''
photo["img_url"] = "https:" + response.css("img.main-photo::attr('src')").get()
photo["tags"] = response.css("ul.tags-list li a[title]::text").getall()
yield photo
def start_requests(self):
for term in self.terms:
self.infinite_scroll_urls.append("https://www.flickr.com/search/?text=" + term)
for url in self.infinite_scroll_urls:
# Load Splash lua script to scroll the page a few times
script = ""
with open("infinite_scroll.lua", "r") as f:
script = f.read()
# Build Splash request
yield SplashRequest(url=url, callback=self.parse, endpoint='execute', args={
"wait": 3,
"timeout": 90,
"lua_source": script,
"headers": {'User-Agent': "Mozilla/5.0 (X11; Linux x86_64; rv:82.0) Gecko/20100101 Firefox/82.0"}
})
def parse(self, response):
for q in response.css(".photo-list-photo-interaction"):
link = q.css("a::attr('href')").get()
yield response.follow(link, self.parse_photo)

View file

@ -0,0 +1,18 @@
function main(splash)
local num_scrolls = 20
local scroll_delay = 0.8
local scroll_to = splash:jsfunc("window.scrollTo")
local get_body_height = splash:jsfunc(
"function() {return document.body.scrollHeight;}"
)
assert(splash:go(splash.args.url))
splash:wait(splash.args.wait)
for _ = 1, num_scrolls do
scroll_to(0, get_body_height())
splash:wait(scroll_delay)
end
return splash:html()
end

5
scrape.sh Executable file
View file

@ -0,0 +1,5 @@
#!/bin/bash
source ./venv/bin/activate.sh
scrapy runspider imgur/spiders/explore.py -o scraped/photos.csv

24412
scraped/photos.csv Normal file

File diff suppressed because one or more lines are too long

11
scrapy.cfg Normal file
View file

@ -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 = imgur.settings
[deploy]
#url = http://localhost:6800/
project = imgur