You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Cannot switch agents in asynchrony
only use async with httpx.AsyncClient(proxies=proxies) as client:
I want to switch agents in a loop, but I can't switch. I want to find a way to switch agents in a loop.
I used this method, but an error was reported
await client.get(url, timeout=20, proxies='http://78.135.87.159:3128')
TypeError: get() got an unexpected keyword argument 'proxy'
Use async with httpx.AsyncClient(limits=limits,proxies=proxies) as client: After crawling a certain amount, the crawler is blocked
`
import asyncio
import time
import httpx
import requests
async def req(client, i, url):
try:
res = await client.get(url, timeout=20)
# res = await client.get(url, timeout=20,proxies=proxies) # ERROR can not use???
print(f'第{i}次请求,status_code = {res.status_code}')
print(res.request.url)
# print(res.headers)
print(res.text)
return res
except Exception as e:
print('error occurred while scraping ',url)
with open('httpxerror.txt',mode='a') as f:
f.write(time.strftime('%Y-%m-%d %H:%M:%S ')+url+'\n')
print(Exception)
time.sleep(1)
raise
async def main():
urllinks = [] # 存放url
PAGE_SIZE = 18
PAGE_NUMBER =1
INDEX_URL = 'https://spa5.scrape.center/api/book/?limit=18&offset={offset}'
task_list = [] # 任务列表
proxypool_url = 'http://127.0.0.1:5555/random'
proxy = requests.get(proxypool_url).text.strip()
print(proxy)
proxies = 'http://' + proxy
# proxies = {'http://78.135.87.159:3128',
# 'http://110.86.181.156:7082'
# }
print(proxies)
limits = httpx.Limits(max_keepalive_connections=5, max_connections=10)
async with httpx.AsyncClient(limits=limits,proxies=proxies) as client:
for page in range(1, PAGE_NUMBER + 1):
urllink = INDEX_URL.format(offset=PAGE_SIZE * (page - 1))
# urllink='https://www.httpbin.org/get'
urllinks.append(urllink)
print(urllinks[page - 1])
res = req(client, page, urllinks[page - 1])
task = asyncio.create_task(res) # 创建任务
task_list.append(task)
await asyncio.gather(*task_list) # 收集任务
if name == 'main':
start = time.time()
asyncio.run(main())
end = time.time()
print(f'time:{end - start}')`
This discussion was converted from issue #2002 on January 03, 2022 15:56.
Heading
Bold
Italic
Quote
Code
Link
Numbered list
Unordered list
Task list
Attach files
Mention
Reference
Menu
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
Cannot switch agents in asynchrony
only use async with httpx.AsyncClient(proxies=proxies) as client:
I want to switch agents in a loop, but I can't switch. I want to find a way to switch agents in a loop.
I used this method, but an error was reported
await client.get(url, timeout=20, proxies='http://78.135.87.159:3128')
TypeError: get() got an unexpected keyword argument 'proxy'
Use async with httpx.AsyncClient(limits=limits,proxies=proxies) as client: After crawling a certain amount, the crawler is blocked
`
import asyncio
import time
import httpx
import requests
async def req(client, i, url):
try:
res = await client.get(url, timeout=20)
# res = await client.get(url, timeout=20,proxies=proxies) # ERROR can not use???
print(f'第{i}次请求,status_code = {res.status_code}')
print(res.request.url)
# print(res.headers)
print(res.text)
return res
except Exception as e:
print('error occurred while scraping ',url)
with open('httpxerror.txt',mode='a') as f:
f.write(time.strftime('%Y-%m-%d %H:%M:%S ')+url+'\n')
print(Exception)
time.sleep(1)
raise
async def main():
urllinks = [] # 存放url
PAGE_SIZE = 18
PAGE_NUMBER =1
INDEX_URL = 'https://spa5.scrape.center/api/book/?limit=18&offset={offset}'
task_list = [] # 任务列表
proxypool_url = 'http://127.0.0.1:5555/random'
proxy = requests.get(proxypool_url).text.strip()
print(proxy)
proxies = 'http://' + proxy
# proxies = {'http://78.135.87.159:3128',
# 'http://110.86.181.156:7082'
# }
print(proxies)
if name == 'main':
start = time.time()
asyncio.run(main())
end = time.time()
print(f'time:{end - start}')`
Beta Was this translation helpful? Give feedback.
All reactions