试图伪造和轮换用户代理
Trying to fake and rotating user agents
我正在尝试伪造用户代理并在 Python 中轮换它们。
我在网上找到了一个关于如何使用 scrapy-useragents 包使用 Scrapy 执行此操作的教程。
我抓取了网页 https://www.whatsmyua.info/，以检查我的用户代理，看看它是否与我的不同，以及它是否旋转。它是否与我的实际用户代理不同，但它不会每次轮换 returns 相同的用户代理，我无法弄清楚出了什么问题。
settings.py
BOT_NAME = 'scrapy_javascript'
SPIDER_MODULES = ['scrapy_javascript.spiders']
NEWSPIDER_MODULE = 'scrapy_javascript.spiders'
# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'scrapy_javascript (+http://www.yourdomain.com)'
# Obey robots.txt rules
ROBOTSTXT_OBEY = True
DOWNLOADER_MIDDLEWARES = {
'scrapy_splash.SplashCookiesMiddleware': 723,
'scrapy_splash.SplashMiddleware': 725,
'scrapy.downloadermiddlewares.httpcompression.HttpCompressionMiddleware': 810,
}
# -----------------------------------------------------------------------------
# USER AGENT
# -----------------------------------------------------------------------------
DOWNLOADER_MIDDLEWARES = {
'scrapy.downloadermiddlewares.useragent.UserAgentMiddleware': None,
'scrapy_useragents.downloadermiddlewares.useragents.UserAgentsMiddleware': 500,
}
USER_AGENTS = [
('Mozilla/5.0 (X11; Linux x86_64) '
'AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/57.0.2987.110 '
'Safari/537.36'), # chrome
('Mozilla/5.0 (X11; Linux x86_64) '
'AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/61.0.3163.79 '
'Safari/537.36'), # chrome
('Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:55.0) '
'Gecko/20100101 '
'Firefox/55.0'), # firefox
('Mozilla/5.0 (X11; Linux x86_64) '
'AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/61.0.3163.91 '
'Safari/537.36'), # chrome
('Mozilla/5.0 (X11; Linux x86_64) '
'AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/62.0.3202.89 '
'Safari/537.36'), # chrome
('Mozilla/5.0 (X11; Linux x86_64) '
'AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/63.0.3239.108 '
'Safari/537.36'), # chrome
]
SPLASH_URL = 'http://199.89.192.74:8050'
DUPEFILTER_CLASS = 'scrapy_splash.SplashAwareDupeFilter'
HTTPCACHE_STORAGE = 'scrapy_splash.SplashAwareFSCacheStorage'
通过创建包含我所有 url 的 csv 文件来解决这个问题，并且它们与 IP 和用户代理配对，因此每次我访问网页时我都会使用这些 IP 和用户代理。然后我不得不在我的蜘蛛中覆盖我的 spalsh_url 这样我的 splash_url 就等于我当时使用的代理。
SplashSpider.py
import csv
from scrapy.spiders import Spider
from scrapy_splash import SplashRequest
from ..items import GameItem
# process the csv file so the url + ip address + useragent pairs are the same as defined in the file
# returns a list of dictionaries, example:
# [ {'url': 'http://www.starcitygames.com/catalog/category/Rivals%20of%20Ixalan',
# 'ip': 'http://204.152.114.244:8050',
# 'ua': "Mozilla/5.0 (BlackBerry; U; BlackBerry 9320; en-GB) AppleWebKit/534.11"},
# ...
# ]
def process_csv(csv_file):
data = []
reader = csv.reader(csv_file)
next(reader)
for fields in reader:
if fields[0] != "":
url = fields[0]
else:
continue # skip the whole row if the url column is empty
if fields[1] != "":
ip = "http://" + fields[1] + ":8050" # adding http and port because this is the needed scheme
if fields[2] != "":
useragent = fields[2]
data.append({"url": url, "ip": ip, "ua": useragent})
return data
class MySpider(Spider):
name = 'splash_spider' # Name of Spider
# notice that we don't need to define start_urls
# just make sure to get all the urls you want to scrape inside start_requests function
# getting all the url + ip address + useragent pairs then request them
def start_requests(self):
# get the file path of the csv file that contains the pairs from the settings.py
with open(self.settings["PROXY_CSV_FILE"], mode="r") as csv_file:
# requests is a list of dictionaries like this -> {url: str, ua: str, ip: str}
requests = process_csv(csv_file)
for req in requests:
# no need to create custom middlewares
# just pass useragent using the headers param, and pass proxy using the meta param
yield SplashRequest(url=req["url"], callback=self.parse, args={"wait": 3},
headers={"User-Agent": req["ua"]},
splash_url = req["ip"],
)
settings.py
BOT_NAME = 'scrapy_javascript'
SPIDER_MODULES = ['scrapy_javascript.spiders']
NEWSPIDER_MODULE = 'scrapy_javascript.spiders'
# Obey robots.txt rules
ROBOTSTXT_OBEY = False
# The path of the csv file that contains the pairs
PROXY_CSV_FILE = "proxies.csv"
DOWNLOADER_MIDDLEWARES = {
'scrapy_splash.SplashCookiesMiddleware': 723,
'scrapy_splash.SplashMiddleware': 725,
'scrapy.downloadermiddlewares.httpcompression.HttpCompressionMiddleware': 810,
}
#SPLASH_URL = 'http://127.0.0.1:8050'
#SPLASH_URL = 'http://localhost:8050'
DUPEFILTER_CLASS = 'scrapy_splash.SplashAwareDupeFilter'
HTTPCACHE_STORAGE = 'scrapy_splash.SplashAwareFSCacheStorage'
# Configure maximum concurrent requests performed by Scrapy (default: 16)
#CONCURRENT_REQUESTS = 16
# 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 = 60
在这里您可以找到 API 返回最常见的用户代理 JSON :
http://51.158.74.109/useragents/?format=json
我已经使用了这个工具，它可以使您的用户代理列表始终更新为最新和最常用的用户代理：https://pypi.org/project/shadow-useragent/
from shadow_useragent import ShadowUserAgent
shadow_useragent = ShadowUserAgent()
print(shadow_useragent.firefox)
# Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:67.0) Gecko/20100101 Firefox/67.0
print(shadow_useragent.chrome)
# Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.169 Safari/537.36
print(shadow_useragent.safari)
# Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_5) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/12.1.1 Safari/605.1.15
print(shadow_useragent.edge)
# Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.140 Safari/537.36 Edge/17.17134
print(shadow_useragent.ie)
# Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; rv:11.0) like Gecko
print(shadow_useragent.android)
# Mozilla/5.0 (Linux; U; Android 4.3; en-us; SM-N900T Build/JSS15J) AppleWebKit/534.30 (KHTML, like Gecko) Version/4.0 Mobile Safari/534.30
print(shadow_useragent.ipad)
# Mozilla/5.0 (iPad; CPU OS 12_3_1 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/12.1.1 Mobile/15E148 Safari/604.1
print(shadow_useragent.random)
# Mozilla/5.0 (Windows NT 6.3; Win64; x64; rv:68.0) Gecko/20100101 Firefox/68.0
print(shadow_useragent.random_nomobile)
# Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.90 Safari/537.36
# and the best one, random via real world browser usage statistic
print(ua.random)
# Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.90 Safari/537.36
# if you want to excluse mobiles (some websites will display different pages)
print(shadow_useragent.random_nomobile)
# Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.90 Safari/537.36
我正在尝试伪造用户代理并在 Python 中轮换它们。
我在网上找到了一个关于如何使用 scrapy-useragents 包使用 Scrapy 执行此操作的教程。
我抓取了网页 https://www.whatsmyua.info/，以检查我的用户代理，看看它是否与我的不同，以及它是否旋转。它是否与我的实际用户代理不同，但它不会每次轮换 returns 相同的用户代理，我无法弄清楚出了什么问题。
settings.py
BOT_NAME = 'scrapy_javascript'
SPIDER_MODULES = ['scrapy_javascript.spiders']
NEWSPIDER_MODULE = 'scrapy_javascript.spiders'
# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'scrapy_javascript (+http://www.yourdomain.com)'
# Obey robots.txt rules
ROBOTSTXT_OBEY = True
DOWNLOADER_MIDDLEWARES = {
'scrapy_splash.SplashCookiesMiddleware': 723,
'scrapy_splash.SplashMiddleware': 725,
'scrapy.downloadermiddlewares.httpcompression.HttpCompressionMiddleware': 810,
}
# -----------------------------------------------------------------------------
# USER AGENT
# -----------------------------------------------------------------------------
DOWNLOADER_MIDDLEWARES = {
'scrapy.downloadermiddlewares.useragent.UserAgentMiddleware': None,
'scrapy_useragents.downloadermiddlewares.useragents.UserAgentsMiddleware': 500,
}
USER_AGENTS = [
('Mozilla/5.0 (X11; Linux x86_64) '
'AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/57.0.2987.110 '
'Safari/537.36'), # chrome
('Mozilla/5.0 (X11; Linux x86_64) '
'AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/61.0.3163.79 '
'Safari/537.36'), # chrome
('Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:55.0) '
'Gecko/20100101 '
'Firefox/55.0'), # firefox
('Mozilla/5.0 (X11; Linux x86_64) '
'AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/61.0.3163.91 '
'Safari/537.36'), # chrome
('Mozilla/5.0 (X11; Linux x86_64) '
'AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/62.0.3202.89 '
'Safari/537.36'), # chrome
('Mozilla/5.0 (X11; Linux x86_64) '
'AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/63.0.3239.108 '
'Safari/537.36'), # chrome
]
SPLASH_URL = 'http://199.89.192.74:8050'
DUPEFILTER_CLASS = 'scrapy_splash.SplashAwareDupeFilter'
HTTPCACHE_STORAGE = 'scrapy_splash.SplashAwareFSCacheStorage'
通过创建包含我所有 url 的 csv 文件来解决这个问题，并且它们与 IP 和用户代理配对，因此每次我访问网页时我都会使用这些 IP 和用户代理。然后我不得不在我的蜘蛛中覆盖我的 spalsh_url 这样我的 splash_url 就等于我当时使用的代理。
SplashSpider.py
import csv
from scrapy.spiders import Spider
from scrapy_splash import SplashRequest
from ..items import GameItem
# process the csv file so the url + ip address + useragent pairs are the same as defined in the file
# returns a list of dictionaries, example:
# [ {'url': 'http://www.starcitygames.com/catalog/category/Rivals%20of%20Ixalan',
# 'ip': 'http://204.152.114.244:8050',
# 'ua': "Mozilla/5.0 (BlackBerry; U; BlackBerry 9320; en-GB) AppleWebKit/534.11"},
# ...
# ]
def process_csv(csv_file):
data = []
reader = csv.reader(csv_file)
next(reader)
for fields in reader:
if fields[0] != "":
url = fields[0]
else:
continue # skip the whole row if the url column is empty
if fields[1] != "":
ip = "http://" + fields[1] + ":8050" # adding http and port because this is the needed scheme
if fields[2] != "":
useragent = fields[2]
data.append({"url": url, "ip": ip, "ua": useragent})
return data
class MySpider(Spider):
name = 'splash_spider' # Name of Spider
# notice that we don't need to define start_urls
# just make sure to get all the urls you want to scrape inside start_requests function
# getting all the url + ip address + useragent pairs then request them
def start_requests(self):
# get the file path of the csv file that contains the pairs from the settings.py
with open(self.settings["PROXY_CSV_FILE"], mode="r") as csv_file:
# requests is a list of dictionaries like this -> {url: str, ua: str, ip: str}
requests = process_csv(csv_file)
for req in requests:
# no need to create custom middlewares
# just pass useragent using the headers param, and pass proxy using the meta param
yield SplashRequest(url=req["url"], callback=self.parse, args={"wait": 3},
headers={"User-Agent": req["ua"]},
splash_url = req["ip"],
)
settings.py
BOT_NAME = 'scrapy_javascript'
SPIDER_MODULES = ['scrapy_javascript.spiders']
NEWSPIDER_MODULE = 'scrapy_javascript.spiders'
# Obey robots.txt rules
ROBOTSTXT_OBEY = False
# The path of the csv file that contains the pairs
PROXY_CSV_FILE = "proxies.csv"
DOWNLOADER_MIDDLEWARES = {
'scrapy_splash.SplashCookiesMiddleware': 723,
'scrapy_splash.SplashMiddleware': 725,
'scrapy.downloadermiddlewares.httpcompression.HttpCompressionMiddleware': 810,
}
#SPLASH_URL = 'http://127.0.0.1:8050'
#SPLASH_URL = 'http://localhost:8050'
DUPEFILTER_CLASS = 'scrapy_splash.SplashAwareDupeFilter'
HTTPCACHE_STORAGE = 'scrapy_splash.SplashAwareFSCacheStorage'
# Configure maximum concurrent requests performed by Scrapy (default: 16)
#CONCURRENT_REQUESTS = 16
# 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 = 60
在这里您可以找到 API 返回最常见的用户代理 JSON :
http://51.158.74.109/useragents/?format=json
我已经使用了这个工具，它可以使您的用户代理列表始终更新为最新和最常用的用户代理：https://pypi.org/project/shadow-useragent/
from shadow_useragent import ShadowUserAgent
shadow_useragent = ShadowUserAgent()
print(shadow_useragent.firefox)
# Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:67.0) Gecko/20100101 Firefox/67.0
print(shadow_useragent.chrome)
# Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.169 Safari/537.36
print(shadow_useragent.safari)
# Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_5) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/12.1.1 Safari/605.1.15
print(shadow_useragent.edge)
# Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.140 Safari/537.36 Edge/17.17134
print(shadow_useragent.ie)
# Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; rv:11.0) like Gecko
print(shadow_useragent.android)
# Mozilla/5.0 (Linux; U; Android 4.3; en-us; SM-N900T Build/JSS15J) AppleWebKit/534.30 (KHTML, like Gecko) Version/4.0 Mobile Safari/534.30
print(shadow_useragent.ipad)
# Mozilla/5.0 (iPad; CPU OS 12_3_1 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/12.1.1 Mobile/15E148 Safari/604.1
print(shadow_useragent.random)
# Mozilla/5.0 (Windows NT 6.3; Win64; x64; rv:68.0) Gecko/20100101 Firefox/68.0
print(shadow_useragent.random_nomobile)
# Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.90 Safari/537.36
# and the best one, random via real world browser usage statistic
print(ua.random)
# Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.90 Safari/537.36
# if you want to excluse mobiles (some websites will display different pages)
print(shadow_useragent.random_nomobile)
# Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.90 Safari/537.36