def download(url):
option = webdriver.ChromeOptions()
# option.add_argument('headless')
option.add_argument('log-level=3')
driver = webdriver.Chrome(
executable_path='.//chromedriver', chrome_options=option)
title = "output"
try:
driver.set_page_load_timeout(15)
driver.get(url)
title = driver.title
except:
print("Timeout - start download anyway.")
print(f'原创力: 《{title}》')
time.sleep(5)
driver.find_element_by_id('btn_preview_remain').click()
time.sleep(2)
frame = driver.find_elements_by_class_name('preview-iframe')[0]
src = frame.get_attribute('src')
print(src)
driver.get(src)
time.sleep(5)
if os.path.exists(f'./temp/{title}'):
shutil.rmtree(f'./temp/{title}')
os.makedirs(f'./temp/{title}')
pageCount = int(driver.find_element_by_id(
'PageCount').get_attribute('innerHTML'))
for i in trange(pageCount):
driver.save_screenshot(f'temp/{title}/capture.png')
page = driver.find_element_by_id('ppt')
left = page.location['x']
top = page.location['y']
right = left + page.size['width']
bottom = top + page.size['height'] - 35
im = Image.open(f'temp/{title}/capture.png')
im = im.crop((left, top, right, bottom)) # 元素裁剪
im.save(f'temp/{title}/{i}.png') # 元素截图
driver.find_element_by_id('pageNext').click()
time.sleep(1) # 防止还没加载出来
os.remove(f'./temp/{title}/capture.png')
driver.quit()
print('下载完毕，正在转码')
conpdf(f'output/{title}.pdf', f'temp/{title}', '.png')
def getPDF(self):
print(self.title)
# 获取需要的信息
self.__getPdfInfo()
# 获得所有图片的地址
img = self.pdfInfo.get('Img')
imgUrl = img if img != None else ""
print('解析地址')
while self.index != self.total:
self.__getNextPage(
self.imgList[-1] if len(self.imgList) != 0 else imgUrl)
self.pbar.close()
# 下载图片
self.__getIMG()
# 生成pdf
print('下载完毕，正在转码')
conpdf(f'output/{self.title}.pdf', f'temp/{self.title}/', '.jpg')
def download(url):
text = requests.get(url).text
pos = text.index('allPage:')
pages = int(text[pos + 8:pos + 12].split(',')[0])
id = url.split('.')[-2].split('-')[-1]
html = BeautifulSoup(text, features='lxml')
title = html.title.string.replace('/', '.')
print(f'豆丁：《{title}》')
if os.path.exists(f'./temp/{title}'):
shutil.rmtree(f'./temp/{title}')
os.makedirs(f'./temp/{title}')
for i in trange(pages):
url = f"http://211.147.220.164/index.jsp?file={id}&width=1600&pageno={i + 1}"
res = requests.get(url)
with open(f'./temp/{title}/{i+1}.jpg', 'wb') as f:
f.write(res.content)
print('下载完毕，正在转码')
conpdf(f'output/{title}.pdf', f'./temp/{title}', '.jpg', True)
def download(url):
option = webdriver.ChromeOptions()
# option.add_argument('headless')
option.add_argument('log-level=3')
driver = webdriver.Chrome(executable_path='.//chromedriver',
chrome_options=option)
title = "output"
try:
driver.set_page_load_timeout(15)
driver.get(url)
title = driver.title
except:
print("Timeout - start download anyway.")
print(f'原创力: 《{title}》')
time.sleep(5)
try:
# 展开全部
elem_cont_button = driver.find_element_by_id("agree_full")
driver.execute_script("arguments[0].scrollIntoView(true);",
elem_cont_button)
actions = ActionChains(driver)
actions.move_to_element(elem_cont_button).perform()
time.sleep(0.5)
elem_cont_button.click()
# time.sleep(10)
except NoSuchElementException:
pass
frame = driver.find_element_by_id('layer_view_iframe')
src = frame.get_attribute('src')
print(src)
driver.get(src)
time.sleep(5)
if os.path.exists(f'./temp/{title}'):
shutil.rmtree(f'./temp/{title}')
os.makedirs(f'./temp/{title}')
pageCount = int(
driver.find_element_by_id('PageCount').get_attribute('innerHTML'))
for i in trange(pageCount):
driver.save_screenshot(f'temp/{title}/capture.png')
page = driver.find_element_by_id('ppt')
left = page.location['x']
top = page.location['y']
right = left + page.size['width']
bottom = top + page.size['height'] - 35
im = Image.open(f'temp/{title}/capture.png')
im = im.crop((left, top, right, bottom)) # 元素裁剪
im.save(f'temp/{title}/{i}.png') # 元素截图
driver.find_element_by_id('pageNext').click()
time.sleep(1) # 防止还没加载出来
os.remove(f'./temp/{title}/capture.png')
driver.quit()
print('下载完毕，正在转码')
conpdf(f'output/{title}.pdf', f'temp/{title}', '.png')
def download(url, callback):
option = webdriver.ChromeOptions()
option.add_argument('headless')
option.add_argument('log-level=3')
driver = webdriver.Chrome(options=option)
title = "output"
try:
# driver.implicitly_wait(15)
driver.set_page_load_timeout(15)
driver.get(url)
title = driver.title
except:
return False, "下载失败，超时"
print(title)
if os.path.exists(f'./output/{title}.pdf'):
return True, title
if 'ppt' in title:
import book118_PPT
driver.quit()
return book118_PPT.download(url, callback)
time.sleep(2)
driver.find_element_by_id("agree_full").click()
time.sleep(1)
driver.get(driver.find_element_by_id(
"layer_new_view_iframe").get_attribute("src"))
time.sleep(3)
while True:
try:
# 展开全部
elem_cont_button = driver.find_element_by_id("btn_read")
driver.execute_script(
"arguments[0].scrollIntoView(true);", elem_cont_button)
actions = ActionChains(driver)
actions.move_to_element(elem_cont_button).perform()
time.sleep(2)
elem_cont_button.click()
except NoSuchElementException:
break
except Exception:
continue
# 获取页数
num_of_pages = driver.find_element_by_class_name(
'page-counts').get_attribute('innerHTML')
num_of_pages = int(num_of_pages.split(' ')[-1])
if os.path.exists(f'./temp/{title}'):
shutil.rmtree(f'./temp/{title}')
os.makedirs(f'./temp/{title}')
elems = driver.find_elements_by_class_name("webpreview-item")
for pages in trange(num_of_pages):
try:
callback(pages, num_of_pages, "正在下载：%s" % title)
elem = elems[pages]
time.sleep(0.5)
actions = ActionChains(driver)
actions.move_to_element(elem).perform()
img = elem.find_element_by_tag_name('img')
img_url = img.get_attribute('src')
if img_url is None or not 'http' in img_url:
img_url = "http:" + img.get_attribute('data-src')
res = requests.get(img_url)
with open(f"./temp/{title}/{pages}.png", "wb") as fh:
fh.write(res.content)
except Exception as e:
print("下载失败！\n%r" % e)
driver.quit()
return False, e
driver.quit()
callback(99, 100, "正在转码")
print('下载完毕，正在转码')
conpdf(f'output/{title}.pdf', f'temp/{title}', '.png')
return True, title
def download(url):
option = webdriver.ChromeOptions()
# option.add_argument('headless')
option.add_argument('log-level=3')
driver = webdriver.Chrome(executable_path='/usr/bin/chromedriver',
chrome_options=option)
title = "output"
try:
driver.set_page_load_timeout(15)
driver.get(url)
title = driver.title
except:
print("Timeout - start download anyway.")
print('道客巴巴: <' + str(title) + '>')
time.sleep(5)
try:
# 展开全部
elem_cont_button = driver.find_element_by_id("continueButton")
driver.execute_script("arguments[0].scrollIntoView(true);",
elem_cont_button)
actions = ActionChains(driver)
actions.move_to_element(elem_cont_button).perform()
time.sleep(0.5)
elem_cont_button.click()
except NoSuchElementException:
pass
# 获取页数
num_of_pages = driver.find_element_by_id(
'readshop'
).find_element_by_class_name('mainpart').find_element_by_class_name(
'shop3').find_element_by_class_name('text').get_attribute('innerHTML')
num_of_pages = int(num_of_pages.split(' ')[-1])
for i in range(5):
# 缩放
driver.find_element_by_id('zoomInButton').click()
time.sleep(0.5)
tempdir = './temp/' + str(title)
if os.path.exists(tempdir):
shutil.rmtree(tempdir)
os.makedirs(tempdir)
for pages in trange(num_of_pages):
time.sleep(0.5)
canvas_id = "page_" + str(pages + 1)
pagepb_id = "pagepb_" + str(pages + 1)
element = driver.find_element_by_id(canvas_id)
driver.execute_script("arguments[0].scrollIntoView(true);", element)
actions = ActionChains(driver)
actions.move_to_element(element).perform()
time.sleep(0.5)
# Check loading status
while (len(
driver.find_element_by_id(pagepb_id).get_attribute(
'innerHTML')) != 0):
time.sleep(1)
# print(driver.find_element_by_id(
# pagepb_id).get_attribute('innerHTML'))
js_cmd = "var canvas = document.getElementById('{}');".format(canvas_id) + \
"return canvas.toDataURL();"
img_data = driver.execute_script(js_cmd)
img_data = (img_data[22:]).encode()
tempPage = './temp/' + str(title) + '/' + str(pages) + '.png'
with open(tempPage, "wb") as fh:
fh.write(base64.decodebytes(img_data))
driver.quit()
print('下载完毕，正在转码')
outputfile = 'output/' + str(title) + '.pdf'
conpdf(outputfile, tempdir, '.png')
def download(url):
option = webdriver.ChromeOptions()
# option.add_argument('headless')
option.add_argument('log-level=3')
driver = webdriver.Chrome(executable_path='.//chromedriver',
chrome_options=option)
title = "output"
try:
# driver.implicitly_wait(15)
driver.set_page_load_timeout(15)
driver.get(url)
title = driver.title
except:
print("Timeout - start download anyway.")
print(title)
time.sleep(5)
while True:
try:
# 展开全部
elem_cont_button = driver.find_element_by_class_name(
"banner-download")
driver.execute_script("arguments[0].scrollIntoView(true);",
elem_cont_button)
actions = ActionChains(driver)
actions.move_to_element(elem_cont_button).perform()
time.sleep(0.5)
driver.find_element_by_class_name("down-arrow").click()
except Exception:
break
# 获取页数
num_of_pages = driver.find_element_by_id(
'readshop').find_element_by_class_name(
'mainpart').find_element_by_class_name(
'shop3').find_elements_by_class_name('text')[-1].get_attribute(
'innerHTML')
num_of_pages = int(num_of_pages.split(';')[-1])
if os.path.exists(f'./temp/{title}'):
shutil.rmtree(f'./temp/{title}')
os.makedirs(f'./temp/{title}')
for pages in trange(num_of_pages):
try:
time.sleep(0.5)
elem = driver.find_element_by_id(f'outer_page_{pages+1}')
actions = ActionChains(driver)
actions.move_to_element(elem).perform()
img = elem.find_element_by_tag_name('img')
img_url = img.get_attribute('src')
res = requests.get(img_url)
with open(f"./temp/{title}/{pages}.gif", "wb") as fh:
fh.write(res.content)
except Exception as e:
print("下载失败！\n%r" % e)
driver.quit()
return
driver.quit()
print('下载完毕，正在转码')
conpdf(f'output/{title}.pdf', f'temp/{title}', '.gif')
def download(url, callback):
option = webdriver.ChromeOptions()
option.add_argument('headless')
option.add_argument('log-level=3')
driver = webdriver.Chrome(chrome_options=option)
title = "output"
try:
driver.set_page_load_timeout(15)
driver.get(url)
title = driver.title[:-8]
except:
return False, "下载失败，超时"
print(f'淘豆网: 《{title}》')
if os.path.exists(f'./output/{title}.pdf'):
return True, title
time.sleep(5)
while True:
try:
driver.execute_script("window.scrollBy(0,10000)")
time.sleep(1)
# 展开全部
elem_cont_button = driver.find_element_by_class_name(
"banner-more-btn")
elem_cont_button = elem_cont_button.find_element_by_tag_name(
'span')
driver.execute_script(
"arguments[0].scrollIntoView(true);", elem_cont_button)
actions = ActionChains(driver)
actions.move_to_element(elem_cont_button).perform()
time.sleep(0.5)
driver.execute_script("arguments[0].click();", elem_cont_button)
# break
except NoSuchElementException:
break
except StaleElementReferenceException:
break
except JavascriptException:
continue
try:
# 获取页数
num_of_pages = driver.find_element_by_id(
'docPage').get_attribute('innerHTML')
num_of_pages = int(num_of_pages)
if os.path.exists(f'./temp/{title}'):
shutil.rmtree(f'./temp/{title}')
os.makedirs(f'./temp/{title}')
for pages in trange(num_of_pages):
callback(pages, num_of_pages, "正在下载：%s" % title)
try:
time.sleep(0.5)
element = driver.find_element_by_id(f"page{pages + 1}")
driver.execute_script("arguments[0].scrollIntoView(true);", element)
actions = ActionChains(driver)
actions.move_to_element(element).perform()
time.sleep(0.5)
imgElement = element.find_element_by_tag_name('img')
imgUrl = imgElement.get_attribute('src')
response = urllib.request.urlopen(imgUrl)
html = response.read()
with open(f'./temp/{title}/{pages}.jpg', 'wb') as f:
f.write(html)
except Exception as e:
print('下载中断，信息：\n%r' % e)
break
driver.quit()
print('下载完毕，正在转码')
callback(99, 100, "正在转码")
conpdf(f'output/{title}.pdf', f'temp/{title}', '.jpg')
return True, title
except Exception as e:
return False, e
def download(url, callback):
option = webdriver.ChromeOptions()
option.add_argument('headless')
option.add_argument('log-level=3')
driver = webdriver.Chrome(chrome_options=option)
title = "output"
try:
driver.set_page_load_timeout(15)
driver.get(url)
title = driver.title
except:
return False, "下载失败，超时"
print(f'新浪爱问: 《{title}》')
if os.path.exists(f'./output/{title}.pdf'):
return True, title
time.sleep(5)
lastPageNum = None
while True:
try:
driver.execute_script("window.scrollBy(0,10000)")
time.sleep(1)
# 展开全部
elem_cont_button = driver.find_element_by_class_name(
"state-bottom")
elem_cont_button = elem_cont_button.find_element_by_tag_name('a')
text = elem_cont_button.find_element_by_tag_name(
'p').get_attribute('innerHTML')
if text == lastPageNum:
print('收费文档！无法下载')
driver.quit()
return
lastPageNum = text
if '结束' in text or '>0</em>' in text:
break
driver.execute_script(
"arguments[0].scrollIntoView(true);", elem_cont_button)
actions = ActionChains(driver)
actions.move_to_element(elem_cont_button).perform()
time.sleep(0.5)
driver.execute_script("arguments[0].click();", elem_cont_button)
except JavascriptException:
continue
try:
# 获取页数
num_of_pages = driver.find_element_by_class_name(
'page-input-con').find_element_by_tag_name('span').get_attribute('innerHTML')
num_of_pages = int(num_of_pages)
driver.execute_script("window.scrollBy(0,10000)")
if os.path.exists(f'./temp/{title}'):
shutil.rmtree(f'./temp/{title}')
os.makedirs(f'./temp/{title}')
imgs = driver.find_elements_by_class_name('data-detail')
for pages in trange(num_of_pages):
callback(pages, num_of_pages, "正在下载：%s" % title)
try:
# svg格式
imgUrl = imgs[pages].find_element_by_tag_name(
'embed').get_attribute('src')
html = requests.get(imgUrl).content
with open(f'./temp/{title}/{pages}.svg', 'wb') as svgFile:
svgFile.write(html)
svgFile.flush()
print(f'rsvg "./temp/{title}/{pages}.svg" "./temp/{title}/{pages}.png" -w 1500 -b white -f png')
os.system(
f'rsvg "./temp/{title}/{pages}.svg" "./temp/{title}/{pages}.png" -w 1500 -b white -f png')
os.remove(f'./temp/{title}/{pages}.svg')
extension = '.png'
except NoSuchElementException:
# 图片格式
while True:
try:
imgUrl = imgs[pages].find_element_by_tag_name(
'img').get_attribute('src')
html = requests.get(imgUrl).content
with open(f'./temp/{title}/{pages}.jpg', 'wb') as f:
f.write(html)
break
except Exception as e:
actions = ActionChains(driver)
actions.move_to_element(imgs[pages]).perform()
time.sleep(1)
driver.execute_script("window.scrollBy(0,10000)")
extension = '.jpg'
driver.quit()
print('下载完毕，正在转码')
callback(99, 100, "正在转码")
conpdf(f'output/{title}.pdf', f'temp/{title}', extension, True)
return True, title
except Exception as e:
return False, e
def download(url):
option = webdriver.ChromeOptions()
# option.add_argument('headless')
option.add_argument('log-level=3')
driver = webdriver.Chrome(
executable_path='.//chromedriver', options=option)
title = "output"
try:
# driver.implicitly_wait(15)
driver.set_page_load_timeout(15)
driver.get(url)
title = driver.title
except:
print("Timeout - start download anyway.")
print(title)
if 'ppt' in title:
import book118_PPT
driver.quit()
book118_PPT.download(url)
return
time.sleep(2)
try:
driver.find_element_by_id("agree_full").click()
except:
try:
driver.find_elements_by_class_name('big')[0].click()
except:
pass
finally:
time.sleep(1)
# driver.get(driver.find_element_by_id(
# "layer_new_view_iframe").get_attribute("src"))
# time.sleep(3)
while True:
try:
# 展开全部
elem_cont_button = driver.find_element_by_id("btn_preview_remain")
driver.execute_script(
"arguments[0].scrollIntoView(true);", elem_cont_button)
actions = ActionChains(driver)
actions.move_to_element(elem_cont_button).perform()
driver.execute_script("window.scrollBy(0, -100)")
time.sleep(2)
elem_cont_button.click()
except NoSuchElementException:
break
except Exception:
import traceback
traceback.print_exc()
finally:
time.sleep(1)
# 获取页数
num_of_pages = driver.find_element_by_class_name(
'counts').get_attribute('innerHTML')
num_of_pages = int(num_of_pages.split(' ')[-1])
if os.path.exists(f'./temp/{title}'):
shutil.rmtree(f'./temp/{title}')
os.makedirs(f'./temp/{title}')
elems = driver.find_elements_by_class_name("webpreview-item")
for pages in trange(num_of_pages):
try:
elem = elems[pages]
time.sleep(0.5)
actions = ActionChains(driver)
actions.move_to_element(elem).perform()
img = elem.find_element_by_tag_name('img')
count = 0
while count < 10 and img.get_attribute('data-src') == None and img.get_attribute('src') == None:
count += 1
time.sleep(1)
img_url = img.get_attribute('src')
if img_url is None or not 'http' in img_url:
img_url = "http:" + img.get_attribute('data-src')
res = requests.get(img_url)
with open(f"./temp/{title}/{pages}.png", "wb") as fh:
fh.write(res.content)
except Exception as e:
print("下载失败！\n%r" % e)
driver.quit()
return
driver.quit()
print('下载完毕，正在转码')
conpdf(f'output/{title}.pdf', f'temp/{title}', '.png')
def download(url):
option = webdriver.ChromeOptions()
option.add_argument('headless')
option.add_argument('log-level=3')
driver = webdriver.Chrome(executable_path='.//chromedriver',
chrome_options=option)
title = "output"
try:
driver.set_page_load_timeout(15)
driver.get(url)
title = driver.title
except:
print("Timeout - start download anyway.")
print(f'新浪爱问: 《{title}》')
time.sleep(5)
lastPageNum = None
while True:
try:
driver.execute_script("window.scrollBy(0,10000)")
time.sleep(1)
# 展开全部
elem_cont_button = driver.find_element_by_class_name(
"state-bottom")
elem_cont_button = elem_cont_button.find_element_by_tag_name('a')
text = elem_cont_button.find_element_by_tag_name(
'p').get_attribute('innerHTML')
if text == lastPageNum:
print('收费文档！无法下载')
driver.quit()
return
lastPageNum = text
if '结束' in text or '>0</em>' in text:
break
driver.execute_script("arguments[0].scrollIntoView(true);",
elem_cont_button)
actions = ActionChains(driver)
actions.move_to_element(elem_cont_button).perform()
time.sleep(0.5)
driver.execute_script("arguments[0].click();", elem_cont_button)
except JavascriptException:
continue
# 获取页数
num_of_pages = driver.find_element_by_class_name(
'page-input-con').find_element_by_tag_name('span').get_attribute(
'innerHTML')
num_of_pages = int(num_of_pages)
driver.execute_script("window.scrollBy(0,10000)")
if os.path.exists(f'./temp/{title}'):
shutil.rmtree(f'./temp/{title}')
os.makedirs(f'./temp/{title}')
imgs = driver.find_elements_by_class_name('data-detail')
for pages in trange(num_of_pages):
try:
# svg格式
imgUrl = imgs[pages].find_element_by_tag_name(
'embed').get_attribute('src')
html = requests.get(imgUrl).content
with open(f'./temp/{title}/{title}.svg', 'wb') as svgFile:
svgFile.write(html)
svgFile.flush()
os.system(
f'svg2png "./temp/{title}/{title}.svg" -o "./temp/{title}/{title}.png" -w 1500'
)
im = Image.open(f'./temp/{title}/{title}.png')
bg = Image.new('RGB', im.size, (255, 255, 255))
bg.paste(im, im)
bg.save(f'./temp/{title}/{pages}.jpg')
os.remove(f'./temp/{title}/{title}.png')
os.remove(f'./temp/{title}/{title}.svg')
except NoSuchElementException:
# 图片格式
while True:
try:
imgUrl = imgs[pages].find_element_by_tag_name(
'img').get_attribute('src')
html = requests.get(imgUrl).content
with open(f'./temp/{title}/{pages}.jpg', 'wb') as f:
f.write(html)
break
except Exception as e:
actions = ActionChains(driver)
actions.move_to_element(imgs[pages]).perform()
time.sleep(1)
driver.execute_script("window.scrollBy(0,10000)")
driver.quit()
print('下载完毕，正在转码')
conpdf(f'output/{title}.pdf', f'temp/{title}', '.jpg', True)
def download(url):
option = webdriver.ChromeOptions()
option.add_argument('headless')
option.add_argument('log-level=3')
option.add_argument("--window-size=1920,1080")
driver = webdriver.Chrome(executable_path='.//chromedriver',
chrome_options=option)
title = "output"
try:
driver.set_page_load_timeout(15)
driver.get(url)
title = driver.title
except:
print("Timeout - start download anyway.")
print(f'道客巴巴: 《{title}》')
time.sleep(5)
try:
# 展开全部
elem_cont_button = driver.find_element_by_id("continueButton")
driver.execute_script("arguments[0].scrollIntoView(true);",
elem_cont_button)
actions = ActionChains(driver)
actions.move_to_element(elem_cont_button).perform()
time.sleep(0.5)
elem_cont_button.click()
except NoSuchElementException:
pass
# 获取页数
num_of_pages = driver.find_element_by_id('toolbar').find_element_by_id('item-page-panel').\
find_element_by_class_name('text').text
num_of_pages = int(num_of_pages.split(' ')[-1])
# print("页数：",num_of_pages)
for i in range(5):
# 缩放
driver.find_element_by_id('zoomInButton').click()
time.sleep(0.5)
if os.path.exists(f'./temp/{title}'):
shutil.rmtree(f'./temp/{title}')
os.makedirs(f'./temp/{title}')
for pages in trange(num_of_pages):
time.sleep(0.5)
canvas_id = "outer_page_" + str(pages + 1)
pagepb_id = "page_" + str(pages + 1)
try:
element = driver.find_element_by_id(canvas_id)
except:
time.sleep(1)
element = driver.find_element_by_id(canvas_id)
driver.execute_script("arguments[0].scrollIntoView(true);", element)
actions = ActionChains(driver)
actions.move_to_element(element).perform()
time.sleep(0.5)
# 执行js代码
js_cmd = "var canvas = document.getElementById('{}');".format(pagepb_id) + \
"return canvas.toDataURL();"
img_data = driver.execute_script(js_cmd)
img_data = (img_data[22:]).encode()
with open(f"./temp/{title}/{pages}.png", "wb") as fh:
fh.write(base64.decodebytes(img_data))
driver.quit()
print('下载完毕，正在转码')
conpdf(f'output/{title}.pdf', f'temp/{title}', '.png')
def download(url, callback):
option = webdriver.ChromeOptions()
option.add_argument('headless')
option.add_argument('log-level=3')
driver = webdriver.Chrome(chrome_options=option)
title = "output"
try:
driver.set_page_load_timeout(15)
driver.get(url)
title = driver.title
except:
return False, "下载失败"
print(f'道客巴巴: 《{title}》')
if os.path.exists(f'./output/{title}.pdf'):
return True, title
time.sleep(5)
try:
# 展开全部
elem_cont_button = driver.find_element_by_id("continueButton")
driver.execute_script(
"arguments[0].scrollIntoView(true);", elem_cont_button)
actions = ActionChains(driver)
actions.move_to_element(elem_cont_button).perform()
time.sleep(0.5)
elem_cont_button.click()
except NoSuchElementException:
pass
try:
# 获取页数
num_of_pages = driver.find_element_by_id('readshop').find_element_by_class_name(
'mainpart').find_element_by_class_name('shop3').find_element_by_class_name('text').get_attribute('innerHTML')
num_of_pages = int(num_of_pages.split(' ')[-1])
for i in range(5):
# 缩放
driver.find_element_by_id('zoomInButton').click()
time.sleep(0.5)
if os.path.exists(f'./temp/{title}'):
shutil.rmtree(f'./temp/{title}')
os.makedirs(f'./temp/{title}')
for pages in trange(num_of_pages):
callback(pages, num_of_pages, "正在下载：%s" % title)
time.sleep(0.5)
canvas_id = "page_" + str(pages + 1)
pagepb_id = "pagepb_" + str(pages + 1)
element = driver.find_element_by_id(canvas_id)
driver.execute_script("arguments[0].scrollIntoView(true);", element)
actions = ActionChains(driver)
actions.move_to_element(element).perform()
time.sleep(0.5)
# Check loading status
while(len(driver.find_element_by_id(pagepb_id).get_attribute('innerHTML')) != 0):
time.sleep(1)
# print(driver.find_element_by_id(
# pagepb_id).get_attribute('innerHTML'))
js_cmd = "var canvas = document.getElementById('{}');".format(canvas_id) + \
"return canvas.toDataURL();"
img_data = driver.execute_script(js_cmd)
img_data = (img_data[22:]).encode()
with open(f"./temp/{title}/{pages}.png", "wb") as fh:
fh.write(base64.decodebytes(img_data))
driver.quit()
print('下载完毕，正在转码')
callback(99, 100, "正在转码")
conpdf(f'output/{title}.pdf', f'temp/{title}', '.png')
return True, title
except Exception as e:
return False, e
