def add_video(document, story):
video_items = analyze_video(story)
if not video_items:
return
para = document.add_paragraph()
run = para.add_run()
font = run.font
font.size = Pt(10)
font.color.rgb = RGBColor(0x7A, 0x7A, 0x7A)
docx_ext.add_hyperlink(para, video_items[0], video_items[1], '4169E1', False)
document.add_picture(video_items[3])
def add_location(document, story):
location_items = analyze_loc(story)
if len(location_items) <= 0:
return
link_name = location_items[2]
google_map_url = 'https://maps.google.com/maps?q=' + location_items[
0] + ',' + location_items[1]
para = document.add_paragraph()
run = para.add_run(u'位置：')
font = run.font
font.size = Pt(10)
font.color.rgb = RGBColor(0x7A, 0x7A, 0x7A)
docx_ext.add_hyperlink(para, google_map_url, link_name, '4169E1', False)
def add_video(document, story):
video_items = analyze_video(story)
if not video_items:
return
para = document.add_paragraph()
run = para.add_run()
font = run.font
font.size = Pt(10)
font.color.rgb = RGBColor(0x7A, 0x7A, 0x7A)
docx_ext.add_hyperlink(para, video_items[0], video_items[1], '4169E1',
False)
try:
document.add_picture(video_items[3], width=Inches(3))
except:
print('视频封面插入出错：' + video_items[3])
def add_quotation(document, quotation):
if not quotation:
return
quotation_items = analyze_quotation(quotation)
para = document.add_paragraph(style='IntenseQuote')
if len(quotation_items) == 1:
run = para.add_run(quotation_items[0])
font = run.font
font.bold = False
font.size = Pt(12)
font.color.rgb = RGBColor(0xA9, 0xA9, 0xA9)
return
run = para.add_run(quotation_items[0] + u'：')
font = run.font
font.bold = False
font.size = Pt(12)
font.color.rgb = RGBColor(0x48, 0xD1, 0xCC)
add_content(document, quotation_items[1] + '\n', para, 12)
# add pictures
filenames = analyze_pic_html(quotation)
for filename in filenames:
try:
run_pic = para.add_run()
run_pic.add_picture(filename, width=Inches(3))
para.add_run('\n')
except:
print '转帖插入图片出错：' + filename
# add video
video_items = analyze_video_html(quotation)
if video_items:
run_video = para.add_run()
font_video = run_video.font
font_video.size = Pt(8)
font_video.color.rgb = RGBColor(0x7A, 0x7A, 0x7A)
docx_ext.add_hyperlink(para, video_items[0], video_items[1], '4169E1',
False)
para.add_run('\n')
try:
run_pic.add_picture(video_items[3], width=Inches(3))
except:
print '视频封面插入出错：' + video_items[3]
# add time
run_time = para.add_run(quotation_items[2])
font_time = run_time.font
font_time.bold = False
font_time.size = Pt(8)
font_time.color.rgb = RGBColor(0x69, 0x69, 0x69)
def add_content(document, content, para=None, font_size=16):
if content.__contains__('k.t.qq.com'):
pattern = re.compile(r'(<a href="http://k.t.qq.com.*?</a>)', re.S)
topics = re.findall(pattern, content)
for topic in topics:
topic_word = topic.split('#')[1]
content = content.replace(
topic, SPLIT_STRING + TOPIC_STRING + '#' + topic_word + '#' +
SPLIT_STRING)
if content.__contains__('www/mb/images/emoji'):
pattern_emoji = re.compile(r'(<img.*?>)', re.S)
pattern_emoji_img = re.compile(r"crs='(.*?)'", re.S)
emojis = re.findall(pattern_emoji, content)
for emoji in emojis:
emoji_url = re.findall(pattern_emoji_img, emoji)[0]
filename = download_pic(emoji_url, PNG_EXTENSION)
content = content.replace(
emoji, SPLIT_STRING + EMOJI_STRING + filename + SPLIT_STRING)
if content.__contains__('em rel="@'):
pattern_friend = re.compile(r'(<em rel=.*?</em>)', re.S)
pattern_friend_name = re.compile(r'<em.*?title="(.*?)"', re.S)
friends = re.findall(pattern_friend, content)
for friend in friends:
friend_name = re.findall(pattern_friend_name, friend)[0]
content = content.replace(
friend,
SPLIT_STRING + FRIEND_STRING + friend_name + SPLIT_STRING)
if content.__contains__('http://url.cn'):
pattern_url = re.compile(r'(<a href=.*?</a>)', re.S)
pattern_url_str = re.compile(r'<a href="(.*?)"', re.S)
urls = re.findall(pattern_url, content)
for url in urls:
url_str = re.findall(pattern_url_str, url)[0]
content = content.replace(
url, SPLIT_STRING + URL_STRING + url_str + SPLIT_STRING)
if content.__contains__('www/mb/images/face'):
pattern_qqemo = re.compile(r'(<img.*?>)', re.S)
pattern_qqemo_img = re.compile(r"crs='(.*?)'", re.S)
qqemos = re.findall(pattern_qqemo, content)
for qqemo in qqemos:
qqemo_url = re.findall(pattern_qqemo_img, qqemo)[0]
filename = download_pic(qqemo_url, GIF_EXTENSION)
content = content.replace(
qqemo, SPLIT_STRING + QQEMO_STRING + filename + SPLIT_STRING)
if content.__contains__('<img class='):
pattern_other_emo = re.compile(r'(<img.*?>)', re.S)
pattern_other_emo_img = re.compile(r'<img.*?crs=(.*?) title=', re.S)
pattern_other_emos = re.findall(pattern_other_emo, content)
for other_emo in pattern_other_emos:
other_emo_url = re.findall(pattern_other_emo_img, other_emo)[0]
other_emo_url = other_emo_url[1:
-1] # delete start and end mark ' "
filename = download_pic(other_emo_url, other_emo_url[-4:])
content = content.replace(
other_emo,
SPLIT_STRING + OTHEREMO_STRING + filename + SPLIT_STRING)
content_parts = content.split(SPLIT_STRING)
if not para:
para = document.add_paragraph()
for content_part in content_parts:
# delete first <div> mark
if content_part.startswith('<div>'):
content_part = content_part[5:]
if content_part.startswith(TOPIC_STRING):
run = para.add_run(content_part.replace(TOPIC_STRING, ''))
font = run.font
font.italic = True
font.bold = False
font.size = Pt(font_size)
font.color.rgb = RGBColor(0x00, 0x00, 0xCD)
elif content_part.startswith(EMOJI_STRING):
run = para.add_run()
filename = content_part.replace(EMOJI_STRING, '')
run.add_picture(filename)
elif content_part.startswith(FRIEND_STRING):
run = para.add_run(content_part.replace(FRIEND_STRING, ''))
font = run.font
font.italic = True
font.bold = False
font.size = Pt(font_size - 2)
font.color.rgb = RGBColor(0xFF, 0x45, 0x00)
elif content_part.startswith(URL_STRING):
docx_ext.add_hyperlink(para, content_part.replace(URL_STRING, ''),
content_part.replace(URL_STRING, ''),
'1E90FF', True)
elif content_part.startswith(QQEMO_STRING):
run = para.add_run()
filename = content_part.replace(QQEMO_STRING, '')
run.add_picture(filename)
elif content_part.startswith(OTHEREMO_STRING):
run = para.add_run()
filename = content_part.replace(OTHEREMO_STRING, '')
run.add_picture(filename)
else:
content_part = content_part.replace('&', '&')
content_part = content_part.replace('>', '>')
content_part = content_part.replace('"', '"')
content_part = content_part.replace('<', '<')
run = para.add_run(content_part)
font = run.font
font.bold = False
font.size = Pt(font_size)
font.color.rgb = RGBColor(0x08, 0x08, 0x08)
def add_content(document, content):
if content.__contains__('k.t.qq.com'):
pattern = re.compile(r'(<a href="http://k.t.qq.com.*?</a>)', re.S)
topics = re.findall(pattern, content)
for topic in topics:
topic_word = topic.split('#')[1]
content = content.replace(
topic, SPLIT_STRING + TOPIC_STRING + '#' + topic_word + '#' +
SPLIT_STRING)
if content.__contains__('www/mb/images/emoji'):
pattern_emoji = re.compile(r'(<img.*?>)', re.S)
pattern_emoji_img = re.compile(r"crs='(.*?)'", re.S)
emojis = re.findall(pattern_emoji, content)
for emoji in emojis:
emoji_url = re.findall(pattern_emoji_img, emoji)[0]
filename = download_pic(emoji_url, PNG_EXTENSION)
content = content.replace(
emoji, SPLIT_STRING + EMOJI_STRING + filename + SPLIT_STRING)
if content.__contains__('em rel="@'):
pattern_friend = re.compile(r'(<em rel=.*?</em>)', re.S)
pattern_friend_name = re.compile(r'<em.*?title="(.*?)"', re.S)
friends = re.findall(pattern_friend, content)
for friend in friends:
friend_name = re.findall(pattern_friend_name, friend)[0]
content = content.replace(
friend,
SPLIT_STRING + FRIEND_STRING + friend_name + SPLIT_STRING)
# delete first <div> mark
content = content[5:]
if content.__contains__('http://url.cn'):
pattern_url = re.compile(r'(<a href=.*?</a>)', re.S)
pattern_url_str = re.compile(r'<a href="(.*?)"', re.S)
urls = re.findall(pattern_url, content)
for url in urls:
url_str = re.findall(pattern_url_str, url)[0]
content = content.replace(
url, SPLIT_STRING + URL_STRING + url_str + SPLIT_STRING)
content_parts = content.split(SPLIT_STRING)
para = document.add_paragraph()
for content_part in content_parts:
if content_part.startswith(TOPIC_STRING):
run = para.add_run(content_part.replace(TOPIC_STRING, ''))
font = run.font
font.italic = True
font.size = Pt(16)
font.color.rgb = RGBColor(0x00, 0x00, 0xCD)
elif content_part.startswith(EMOJI_STRING):
run = para.add_run()
filename = content_part.replace(EMOJI_STRING, '')
run.add_picture(filename)
elif content_part.startswith(FRIEND_STRING):
run = para.add_run(content_part.replace(FRIEND_STRING, ''))
font = run.font
font.italic = True
font.size = Pt(16)
font.color.rgb = RGBColor(0xFF, 0x45, 0x00)
elif content_part.startswith(URL_STRING):
docx_ext.add_hyperlink(para, content_part.replace(URL_STRING, ''),
content_part.replace(URL_STRING, ''),
'1E90FF', True)
else:
run = para.add_run(content_part)
font = run.font
font.size = Pt(16)
font.color.rgb = RGBColor(0x08, 0x08, 0x08)
