Related
I need help with my webcrawler.
I got an invalid syntax here:
"f.write("{},{},{}\n".format(word,url,count))"
and also when I command "scrapy crawl FirstSpider > wordlist.csv" a csv file shows up but either is empty or not as structured as I want it to be.
I want to crawl 300 websites and need the data as structured as possible.
How can I get a csv file with the urls structured and then the count of the certain keywords next to it,
from scrapy.spiders import CrawlSpider, Rule
from scrapy.linkextractors import LinkExtractor
from scrapy.item import Item
import requests
def find_all_substrings(string, sub):
import re
starts = [match.start() for match in re.finditer(re.escape(sub), string)]
return starts
class FirstSpider(CrawlSpider):
name = "FirstSpider"
allowed_domains = ["www.example.com"]
start_urls = ["https://www.example.com/"]
rules = [Rule(LinkExtractor(), follow=True, callback="check_buzzwords")]
crawl_count = 0
words_found = 0
def check_buzzwords(self, response):
self.__class__.crawl_count += 1
wordlist = [
"keyword1",
"keyword2",
"keyword3"
]
url = response.url
data = response.body.decode('utf-8')
count = 0
for word in wordlist:
substrings = find_all_substrings(data, word)
count = 0
word_counts = {}
links = []
"f = open('wordlist.csv', 'w')"
for pos in substrings:
ok = False
if not ok:
count += 1
word_counts[word] = {url: count}
for link in links:
page = requests.get(link)
data = page.text
for word in wordlist:
substrings = find_all_substrings(data, word)
count = 0
for word in wordlist:
substrings = find_all_substrings(data, word)
for pos in substrings:
ok = False
if not ok:
"f.write("{},{},{}\n".format(word,url,count))"
self.__class__.words_found += 1
print(word + ";" + url + ";" + str(count) + ";")
with open('wordlist.csv', 'w') as f:
for word, data in word_counts.items():
for url, count in data.items():
f.write("{},{},{}\n".format(word, url, count))
f.close()
return Item()
def _requests_to_follow(self, response):
if getattr(response, "encoding", None) != None:
return CrawlSpider._requests_to_follow(self, response)
else:
return []
I want to crawl websites for certain keywords (wordlist). My output should be a csv file with the following information: url, count of keyword found on the website.
I got an invalid syntax for the following ``` "f.write("{},{},{}\n".format(word,url,count))"
And the output csv file is often empty or does not crawl all the urls.
You have unnecessary quotation marks around lines 41 and 61
line 41 ---> "f = open('wordlist.csv', 'w')"
line 61 ---> "f.write("{},{},{}\n".format(word,url,count))"
Also usually you don't need to manually save data to a file because Scrapy has a built-in mechanism - Feed export
By using FEED_EXPORT_FIELDS setting you can specify which fields of the item should be exported and their order.
Here is the command to run the spider and save data to a file:
scrapy crawl FirstSpider -O url.csv
-O (capital 'O') means "rewrite a file"
-o (lowercase 'o') means "append to an existent file".
Hope you help me, I want to get flow info from switch and that by sending a request every 10s and the switch reply with the info but I get the following error when the controller receive the reply by using a flow request reply handler The error is occuring because of flow matching 'eth_type'
CollectTrainingStatsApp: Exception occurred during handler processing. Backtrace from offending handler [_flow_stats_reply_handler] servicing event [EventOFPFlowStatsReply] follows.
Traceback (most recent call last):
File "/usr/local/lib/python2.7/dist-packages/ryu/base/app_manager.py", line 290, in _event_loop
handler(ev)
File "/home/guenfaf/Documents/Training ryu/data_to_csv/data_to_csv.py", line 59, in _flow_stats_reply_handler
for stat in sorted([flow for flow in body if (flow.priority == 1) ], key=lambda flow:
File "/home/guenfaf/Documents/Training ryu/data_to_csv/data_to_csv.py", line 60, in <lambda>
(flow.match['eth_type'],flow.match['ipv4_src'],flow.match['ipv4_dst'],flow.match['ip_proto'])):
File "/usr/local/lib/python2.7/dist-packages/ryu/ofproto/ofproto_v1_3_parser.py", line 904, in __getitem__
return dict(self._fields2)[key]
KeyError: 'eth_type'
Here is my code :
from ryu.app import simple_switch_13
from ryu.controller import ofp_event
from ryu.controller.handler import MAIN_DISPATCHER, DEAD_DISPATCHER
from ryu.controller.handler import set_ev_cls
from ryu.lib import hub
from time import time
# class CollectTrainingStatsApp(simple_switch_13.SimpleSwitch13):
class CollectTrainingStatsApp(simple_switch_13.SimpleSwitch13):
def __init__(self, *args, **kwargs):
super(CollectTrainingStatsApp, self).__init__(*args, **kwargs)
self.datapaths = {}
self.monitor_thread = hub.spawn(self.monitor)
file0 = open("FlowStatsfile.csv","w")
file0.write('datapath_id,flow_id,ip_src,tp_src,ip_dst,tp_dst,ip_proto,flow_duration_sec,flow_duration_nsec,idle_timeout,hard_timeout,flags,packet_count,byte_count,packet_count_per_second,packet_count_per_nsecond,byte_count_per_second,byte_count_per_nsecond,label\n')
file0.close()
#Asynchronous message
#set_ev_cls(ofp_event.EventOFPStateChange,[MAIN_DISPATCHER, DEAD_DISPATCHER])
def state_change_handler(self, ev):
datapath = ev.datapath
if ev.state == MAIN_DISPATCHER:
if datapath.id not in self.datapaths:
self.logger.debug('register datapath: %016x', datapath.id)
self.datapaths[datapath.id] = datapath
elif ev.state == DEAD_DISPATCHER:
if datapath.id in self.datapaths:
self.logger.debug('unregister datapath: %016x', datapath.id)
del self.datapaths[datapath.id]
def monitor(self):
while True:
for dp in self.datapaths.values():
self.request_stats(dp)
hub.sleep(10)
def request_stats(self, datapath):
self.logger.debug('send stats request: %016x', datapath.id)
parser = datapath.ofproto_parser
req = parser.OFPFlowStatsRequest(datapath)
datapath.send_msg(req)
#set_ev_cls(ofp_event.EventOFPFlowStatsReply, MAIN_DISPATCHER)
def _flow_stats_reply_handler(self, ev):
#timestamp = time.time()
tp_src = 0
tp_dst = 0
file0 = open("FlowStatsfile.csv","a+")
body = ev.msg.body
for stat in sorted([flow for flow in body if (flow.priority == 1) ], key=lambda flow:
(flow.match['eth_type'],flow.match['ipv4_src'],flow.match['ipv4_dst'],flow.match['ip_proto'])):
ip_src = stat.match['ipv4_src']
ip_dst = stat.match['ipv4_dst']
ip_proto = stat.match['ip_proto']
if stat.match['ip_proto'] == 1:
icmp_code = stat.match['icmpv4_code']
icmp_type = stat.match['icmpv4_type']
elif stat.match['ip_proto'] == 6:
tp_src = stat.match['tcp_src']
tp_dst = stat.match['tcp_dst']
elif stat.match['ip_proto'] == 17:
tp_src = stat.match['udp_src']
tp_dst = stat.match['udp_dst']
flow_id = str(ip_src) + str(tp_src) + str(ip_dst) + str(tp_dst) + str(ip_proto)
try:
packet_count_per_second = stat.packet_count/stat.duration_sec
packet_count_per_nsecond = stat.packet_count/stat.duration_nsec
except:
packet_count_per_second = 0
packet_count_per_nsecond = 0
try:
byte_count_per_second = stat.byte_count/stat.duration_sec
byte_count_per_nsecond = stat.byte_count/stat.duration_nsec
except:
byte_count_per_second = 0
byte_count_per_nsecond = 0
file0.write("{},{},{},{},{},{},{},{},{},{},{},{},{},{},{},{},{},{},{},{},{}\n"
.format(ev.msg.datapath.id, flow_id, ip_src, tp_src,ip_dst, tp_dst,
stat.match['ip_proto'],
stat.duration_sec, stat.duration_nsec,
stat.idle_timeout, stat.hard_timeout,
stat.flags, stat.packet_count,stat.byte_count,
packet_count_per_second,packet_count_per_nsecond,
byte_count_per_second,byte_count_per_nsecond,0))
file0.close()
For my job, I built a scrapy spider to quickly check in on ~200-500 website landing pages for clues that the pages are not functioning, outside of just 400-style errors. (e.g. check for the presence of "out of stock" on page.) This check happens across approx. 30 different websites under my purview, all of them using the same page structure.
This has worked fine, every day, for 4 months.
Then, suddenly, and without change to the code, I started getting unpredictable errors, about 4 weeks ago:
url_title = response.css("title::text").extract_first()
AttributeError: 'Response' object has no attribute 'css'
If I run this spider, this error will occur with, say... 3 out of 400 pages.
Then, if immediately run the spider again, those same 3 pages are scraped just fine without error, and 4 totally different pages will return the same error.
Furthermore, if I run the EXACT same spider as below, but replace mapping with just these 7 erroneous landing pages, they are scraped perfectly fine.
Is there something in my code that's not quite right??
I'm going to attach the whole code - sorry in advance!! - I just fear that something I might deem as superfluous may in fact be the cause. So this is the whole thing, but with sensitive data replaced with ####.
I've checked all of the affected pages, and of course the css is valid, and the title is always present.
I've done sudo apt-get update & sudo apt-get dist-upgrade on the server running scrapy, in hopes that this would help. No luck.
import scrapy
from scrapy import signals
from sqlalchemy.orm import sessionmaker
from datetime import date, datetime, timedelta
from scrapy.http.request import Request
from w3lib.url import safe_download_url
from sqlalchemy import and_, or_, not_
import smtplib
from email.MIMEMultipart import MIMEMultipart
from email.MIMEText import MIMEText
from sqlalchemy.engine import create_engine
engine = create_engine('mysql://######:#######localhost/LandingPages', pool_recycle=3600, echo=False)
#conn = engine.connect()
from LandingPageVerifier.models import LandingPagesFacebook, LandingPagesGoogle, LandingPagesSimplifi, LandingPagesScrapeLog, LandingPagesScrapeResults
Session = sessionmaker(bind=engine)
session = Session()
# today = datetime.now().strftime("%Y-%m-%d")
# thisyear = datetime.now().strftime("%Y")
# thismonth = datetime.now().strftime("%m")
# thisday = datetime.now().strftime("%d")
# start = date(year=2019,month=04,day=09)
todays_datetime = datetime(datetime.today().year, datetime.today().month, datetime.today().day)
print todays_datetime
landingpages_today_fb = session.query(LandingPagesFacebook).filter(LandingPagesFacebook.created_on >= todays_datetime).all()
landingpages_today_google = session.query(LandingPagesGoogle).filter(LandingPagesGoogle.created_on >= todays_datetime).all()
landingpages_today_simplifi = session.query(LandingPagesSimplifi).filter(LandingPagesSimplifi.created_on >= todays_datetime).all()
session.close()
#Mix 'em together!
landingpages_today = landingpages_today_fb + landingpages_today_google + landingpages_today_simplifi
#landingpages_today = landingpages_today_fb
#Do some iterating and formatting work
landingpages_today = [(u.ad_url_full, u.client_id) for u in landingpages_today]
#print landingpages_today
landingpages_today = list(set(landingpages_today))
#print 'Unique pages: '
#print landingpages_today
# unique_landingpages = [(u[0]) for u in landingpages_today]
# unique_landingpage_client = [(u[1]) for u in landingpages_today]
# print 'Pages----->', len(unique_landingpages)
class LandingPage004Spider(scrapy.Spider):
name='LandingPage004Spider'
#classmethod
def from_crawler(cls, crawler, *args, **kwargs):
spider = super(LandingPage004Spider, cls).from_crawler(crawler, *args, **kwargs)
#crawler.signals.connect(spider.spider_opened, signals.spider_opened)
crawler.signals.connect(spider.spider_closed, signals.spider_closed)
return spider
def spider_closed(self, spider):
#stats = spider.crawler.stats.get_stats()
stats = spider.crawler.stats.get_value('item_scraped_count'),
Session = sessionmaker(bind=engine)
session = Session()
logitem = LandingPagesScrapeLog(scrape_count = spider.crawler.stats.get_value('item_scraped_count'),
is200 = spider.crawler.stats.get_value('downloader/response_status_count/200'),
is400 = spider.crawler.stats.get_value('downloader/response_status_count/400'),
is403 = spider.crawler.stats.get_value('downloader/response_status_count/403'),
is404 = spider.crawler.stats.get_value('downloader/response_status_count/404'),
is500 = spider.crawler.stats.get_value('downloader/response_status_count/500'),
scrapy_errors = spider.crawler.stats.get_value('log_count/ERROR'),
scrapy_criticals = spider.crawler.stats.get_value('log_count/CRITICAL'),
)
session.add(logitem)
session.commit()
session.close()
#mapping = landingpages_today
handle_httpstatus_list = [200, 302, 404, 400, 500]
start_urls = []
def start_requests(self):
for url, client_id in self.mapping:
yield Request(url, callback=self.parse, meta={'client_id': client_id})
def parse(self, response):
##DEBUG - return all scraped data
#wholepage = response.body.lower()
url = response.url
if 'redirect_urls' in response.request.meta:
redirecturl = response.request.meta['redirect_urls'][0]
if 'utm.pag.ca' in redirecturl:
url_shortener = response.request.meta['redirect_urls'][0]
else:
url_shortener = 'None'
else:
url_shortener = 'None'
client_id = response.meta['client_id']
url_title = response.css("title::text").extract_first()
# pagesize = len(response.xpath('//*[not(descendant-or-self::script)]'))
pagesize = len(response.body)
HTTP_code = response.status
####ERROR CHECK: Small page size
if 'instapage' in response.body.lower():
if pagesize <= 20000:
err_small = 1
else:
err_small = 0
else:
if pagesize <= 35000:
err_small = 1
else:
err_small = 0
####ERROR CHECK: Page contains the phrase 'not found'
if 'not found' in response.xpath('//*[not(descendant-or-self::script)]').extract_first().lower():
#their sites are full of HTML errors, making scrapy unable to notice what is and is not inside a script element
if 'dealerinspire' in response.body.lower():
err_has_not_found = 0
else:
err_has_not_found = 1
else:
err_has_not_found = 0
####ERROR CHECK: Page cotains the phrase 'can't be found'
if "can't be found" in response.xpath('//*[not(self::script)]').extract_first().lower():
err_has_cantbefound = 1
else:
err_has_cantbefound = 0
####ERROR CHECK: Page contains the phrase 'unable to locate'
if 'unable to locate' in response.body.lower():
err_has_unabletolocate = 1
else:
err_has_unabletolocate = 0
####ERROR CHECK: Page contains phrase 'no longer available'
if 'no longer available' in response.body.lower():
err_has_nolongeravailable = 1
else:
err_has_nolongeravailable = 0
####ERROR CHECK: Page contains phrase 'no service specials'
if 'no service specials' in response.body.lower():
err_has_noservicespecials = 1
else:
err_has_noservicespecials = 0
####ERROR CHECK: Page contains phrase 'Sorry, no' to match zero inventory for a search, which normally says "Sorry, no items matching your request were found."
if 'sorry, no ' in response.body.lower():
err_has_sorryno = 1
else:
err_has_sorryno = 0
yield {'client_id': client_id, 'url': url, 'url_shortener': url_shortener, 'url_title': url_title, "pagesize": pagesize, "HTTP_code": HTTP_code, "err_small": err_small, 'err_has_not_found': err_has_not_found, 'err_has_cantbefound': err_has_cantbefound, 'err_has_unabletolocate': err_has_unabletolocate, 'err_has_nolongeravailable': err_has_nolongeravailable, 'err_has_noservicespecials': err_has_noservicespecials, 'err_has_sorryno': err_has_sorryno}
#E-mail settings
def sendmail(recipients,subject,body):
fromaddr = "#######"
toaddr = recipients
msg = MIMEMultipart()
msg['From'] = fromaddr
msg['Subject'] = subject
body = body
msg.attach(MIMEText(body, 'html'))
server = smtplib.SMTP('########)
server.starttls()
server.login(fromaddr, "##########")
text = msg.as_string()
server.sendmail(fromaddr, recipients, text)
server.quit()
`
Expected results is a perfect scrape, with no errors.
Actual results are unpredicatable AttributeErrors, claiming that attribute 'css' can't be found on some pages. But if I scrape those pages individually, using the same script, they scrape just fine.
Sometimes Scrapy can't parse HTML because of markup errors, that's why you can't call response.css(). You can catch these events in your code and analyze broken HTML:
def parse(self, response):
try:
....
your code
.....
except:
with open("Error.htm", "w") as f:
f.write(response.body)
UPDATE You can try to check for empty response:
def parse(self, response):
if not response.body:
yield scrapy.Request(url=response.url, callback=self.parse, meta={'client_id': response.meta["client_id"]})
# your original code
I am trying to make this code output to a csv file when calling the spider with -o output.csv
# -*- coding: utf-8 -*-
import scrapy
from scrapy.spiders import SitemapSpider
from scrapy.spiders import Spider
from scrapy.http import Request, XmlResponse
from scrapy.utils.sitemap import Sitemap, sitemap_urls_from_robots
from scrapy.utils.gz import gunzip, is_gzipped
import re
import requests
class GetpagesfromsitemapSpider(SitemapSpider):
name = "test"
handle_httpstatus_list = [404]
def parse(self, response):
print response.url
def _parse_sitemap(self, response):
if response.url.endswith('/robots.txt'):
for url in sitemap_urls_from_robots(response.body):
yield Request(url, callback=self._parse_sitemap)
else:
body = self._get_sitemap_body(response)
if body is None:
self.logger.info('Ignoring invalid sitemap: %s', response.url)
return
s = Sitemap(body)
sites = []
if s.type == 'sitemapindex':
for loc in iterloc(s, self.sitemap_alternate_links):
if any(x.search(loc) for x in self._follow):
yield Request(loc, callback=self._parse_sitemap)
elif s.type == 'urlset':
for loc in iterloc(s):
for r, c in self._cbs:
if r.search(loc):
sites.append(loc)
break
print sites
def __init__(self, spider=None, *a, **kw):
super(GetpagesfromsitemapSpider, self).__init__(*a, **kw)
self.spider = spider
l = []
url = "https://channelstore.roku.com"
resp = requests.head(url + "/sitemap.xml")
if (resp.status_code != 404):
l.append(resp.url)
else:
resp = requests.head(url + "/robots.txt")
if (resp.status_code == 200):
l.append(resp.url)
self.sitemap_urls = l
print self.sitemap_urls
def iterloc(it, alt=False):
for d in it:
yield d['loc']
# Also consider alternate URLs (xhtml:link rel="alternate")
if alt and 'alternate' in d:
for l in d['alternate']:
yield l
I have tried changing the print response url on line 18 to a few things but I cant seem to make this script output to a CSV, all I can manage is seeing the exact information I want but on the terminal screen.
This code is from here but I am not working well with the easy part of completing the code.
Any help is greatly appreciated!
Not clear from your example, but it looks like you are not passing the command line arguments (-o) to your SitemapSpider.
A simpler solution, instead of passing the -o argument, is to just redirect your output to a file:
my_script.py > output.csv
OR
my_script.py | tee output.csv <-- this way will write to file, and also output in your terminal
EDIT:
Not the most efficient way, but without seeing a full script:
def parse(self, response):
with open('output.csv', 'a') as fh:
fh.write('{}\n'.format(response.url))
This will append each response.url to a new line in the output.csv file
My Code.
#!/usr/bin/env python
#coding: utf-8
userid="NicoNicoCreate#gmail.com"
passwd="********"
import sys, re, cgi, urllib, urllib.request, urllib.error, http.cookiejar, xml.dom.minidom, time, urllib.parse
import simplejson as json
def getToken():
html = urllib.request.urlopen("http://www.nicovideo.jp/my/mylist").read()
for line in html.splitlines():
mo = re.match(r'^\s*NicoAPI\.token = "(?P<token>[\d\w-]+)";\s*',line)
if mo:
token = mo.group('token')
break
assert token
return token
def mylist_create(name):
cmdurl = "http://www.nicovideo.jp/api/mylistgroup/add"
q = {}
q['name'] = name.encode("utf-8")
q['description'] = ""
q['public'] = 0
q['default_sort'] = 0
q['icon_id'] = 0
q['token'] = token
cmdurl += "?" + urllib.parse.urlencode(q).encode("utf-8")
j = json.load( urllib.request.urlopen(cmdurl), encoding='utf-8')
return j['id']
def addvideo_tomylist(mid,smids):
for smid in smids:
cmdurl = "http://www.nicovideo.jp/api/mylist/add"
q = {}
q['group_id'] = mid
q['item_type'] = 0
q['item_id'] = smid
q['description'] = u""
q['token'] = token
cmdurl += "?" + urllib.parse.urlencode(q).encode("utf-8")
j = json.load( urllib.request.urlopen(cmdurl), encoding='utf-8')
time.sleep(0.5)
#Login
opener = urllib.request.build_opener(urllib.request.HTTPCookieProcessor(http.cookiejar.CookieJar()))
urllib.request.install_opener(opener)
urllib.request.urlopen("https://secure.nicovideo.jp/secure/login",
urllib.parse.urlencode( {"mail":userid, "password":passwd}) ).encode("utf-8")
#GetToken
token = getToken()
#MakeMylist&AddMylist
mid = mylist_create(u"Testlist")
addvideo_tomylist(mid, ["sm9","sm1097445", "sm1715919" ] )
MyError.
Traceback (most recent call last):
File "Nico3.py", line 48, in <module>
urllib.parse.urlencode( {"mail":userid, "password":passwd}) ).encode("utf-8")
File "/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/urllib/request.py", line 162, in urlopen
return opener.open(url, data, timeout)
File "/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/urllib/request.py", line 463, in open
req = meth(req)
File "/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/urllib/request.py", line 1170, in do_request_
raise TypeError(msg)
TypeError: POST data should be bytes or an iterable of bytes. It cannot be of type str.
I've tried encode but it did not help.
I'm japanese accademic students.
It was not able to be settled by my knowledge.
I am aware of this similar question, TypeError: POST data should be bytes or an iterable of bytes. It cannot be str, but am too new for the answer to be much help.
You paren is in the wrong place so you are not actually encoding:
.urlencode({"mail":userid, "password":passwd}).encode("utf-8")) # <- move inside