问加速图像网络刮刀

EN

pip3 install lxml

Could not find a version that satisfies the requirement python-lxml (from versions: )
No matching distribution found for python-lxml

import re
import time
import requests
import itertools
from requests import get
from bs4 import BeautifulSoup as bs

def generate_comic_link(array, num):
  for link in itertools.islice(array, 0, num):
    yield link

def grab_image_src_url(link):
  req = requests.get(link)
  comic = req.text
  soup = bs(comic, 'html.parser')
  for i in soup.find_all('p'):
    for img in i.find_all('img', src=True):
      return img['src']

def download_image(link):
  file_name = url.split('/')[-1]
  with open(file_name, "wb") as file:
    response = get(url)
    file.write(response.content)

def fetch_comic_archive():
  url = 'http://www.poorlydrawnlines.com/archive/'
  req = requests.get(url)
  page = req.text
  soup = bs(page, 'html.parser')
  all_links = []
  for link in soup.find_all('a'):
    all_links.append(link.get('href'))
  return all_links

def filter_comic_archive(archive):
  pattern = re.compile(r'http://www.poorlydrawnlines.com/comic/.+')
  filtered_links = [i for i in archive if pattern.match(i)]
  return filtered_links

all_comics = fetch_comic_archive()
found_comics = filter_comic_archive(all_comics)

print("\nThe scraper has found {} comics.".format(len(found_comics)))
print("How many comics do you want to download?")
n_of_comics = int(input(">> ").strip())

start = time.time()
for link in generate_comic_link(found_comics, n_of_comics):
  print("Downloading: {}".format(link)
  url = grab_image_src_url(link)
  download_image(url)
end = time.time()
print("Successfully downloaded {} comics in {:.2f} seconds.".format(n_of_comics, end - start))