test

test.py

import requests
from lxml import html
from PIL import Image
import io
from itertools import starmap

def grab_list(url):
    title_path = '//td[@class="huanhang"]/a/text()'
    link_path = '//td[@class="huanhang"]/a/@href'
    raw_data = html.fromstring(requests.get(url).text)
    return tuple(zip([i.strip() for i in raw_data.xpath(title_path)], raw_data.xpath(link_path)))
    
def grab_target_base_url(src):
    raw = html.fromstring(requests.get(src).text)
    base_path = '//input[@id="dp"]/@value'
    return raw.xpath(base_path)[0]
  
  def grab_target_gifs(base_url):
    ret = []
    start = 1
    while 1:
        resp = requests.get(base_url + str(start) + ".gif")
        if not resp.headers['Content-Type'] == 'image/gif':
            break
        ret.append(resp.content)
        start += 1
    return ret
  
  def compose_to_pdf(gifs_data, save_path):
    gifs = [Image.open(io.BytesIO(i)) for i in gifs_data]
    gifs[0].save(save_path + ".pdf", "PDF" ,resolution=100.0, save_all=True, append_images=gifs[1:])
    print("Success! %s" % save_path)
    return True
  
  
  def download_pdf(filename, src, dir="reports/"):
    return compose_to_pdf(grab_target_gifs(grab_target_base_url(src)), dir + filename)
  
  def lets_go(url):
    return list(starmap(download_pdf, grab_list(url)))