def craw(url, page):
html1 = urllib.request.urlopen(url).read()
html1 = str(html1)
print(html1)
pat1 = '<div id="plist".+? <div class="page clearfix">'
result1 = retest.compile(pat1).findall(html1)
print("=============")
print(result1)
result1 = result1[0]
print("=============")
print(result1)
pat2 = '<img width="220" height="220" data-img="1" src="//(.+?\.jpg)">'
imagelist = retest.compile(pat2).findall(result1)
print("=============????????")
print(imagelist)
x = 1
for imageurl in imagelist:
imagename = "E:/learn/GitHub/pythoncrawl/img1/" + str(page) + str(
x) + '.jpg'
imageurl = "http://" + imageurl
try:
urllib.request.urlretrieve(imageurl, filename=imagename)
except urllib.error.URLError as e:
if hasattr(e, "code"):
x += 1
if hasattr(e, "reason"):
x += 1
x += 1
def parse(self, response):
# pass
item = QtpjtItem()
paturl="(http://pic.qiantucdn.com/58pic/.*?).jpg"
item["picurl"] = retest.compile(paturl).findall(str(response.body))
patlocal = "http://pic.qiantucdn.com/58pic/.*?/.*?/.*?/(.*?).jpg"
item["picid"] = retest.compile(patlocal).findall(str(response.body))
yield item
for i in range(1,201):
nexturl="http://www.58pic.com/tb/id-"+str(i)+".html"
yield Request(nexturl,callback=self.parse)
def parse(self, response):
# pass
item = HexunpjtItem()
item['name'] = response.xpath(
"//span[@class='ArticleTitleText']/a/text()").extract()
item["url"] = response.xpath(
"//span[@class='ArticleTitleText']/a/@href").extract()
pat1 = '<script type="text/javascript" src="(http://click.tool.hexun.com/.*?)">'
hcurl = retest.compile(pat1).findall(str(response.body))[0]
headers2 = (
"User-Agent",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/38.0.2125.122 Safari/537.36 SE 2.X MetaSr 1.0"
)
opener = urllib.request.build_opener()
opener.addheaders = [headers2]
# 将opener安装为全局
urllib.request.install_opener(opener)
#data为对应博客列表页的所有博文的点击数与评论数数据
data = urllib.request.urlopen(hcurl).read()
#pat2为提取文章阅读数的正则表达式
pat2 = "click\d*?','(\d*?)'"
#pat3为提取文章评论数的正则表达式
pat3 = "comment\d*?','(\d*?)'"
#提取阅读数和评论数数据并分别赋值给item下的hits和comment
item["hits"] = retest.compile(pat2).findall(str(data))
item["comment"] = retest.compile(pat3).findall(str(data))
yield item
#提取博文列表页的总页数
pat4 = "blog.hexun.com/p(.*?)/"
#通过正则表达式获取到的数据为一个列表，倒数第二个元素为总页数
data2 = retest.compile(pat4).findall(str(response.body))
if (len(data2) >= 2):
totalurl = data2[-2]
else:
totalurl = 1
#在实际运行中，下一行print的代码可以注释掉，在调试过程中，可以开启下一行print的代码
#print("一共"+str(totalurl)+"页")
#进入for循环，依次爬取各博文列表页的博文数据
for i in range(2, int(totalurl) + 1):
#构造下一次要爬取的url，爬取一下页博文列表页中的数据
nexturl = "http://" + str(
self.uid) + ".blog.hexun.com/p" + str(i) + "/default.html"
#进行下一次爬取，下一次爬取仍然模拟成浏览器进行
yield Request(
nexturl,
callback=self.parse,
headers={
'User-Agent':
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/38.0.2125.122 Safari/537.36 SE 2.X MetaSr 1.0"
})
def run(self):
page = self.pagestart
keycode = urllib.request.quote("key")
pagecode = urllib.request.quote("&queue")
for page in range(self.pagestart, self.pageend + 1):
url = "http://weixin.sougou.com/weixin?type=2&query=" + keycode + pagecode + str(
page)
data1 = use_proxy(self.proxy, url)
listurlpat = '<div class="txt_box">.*?(http://.*)"'
listurl.append(retest.compile(listurlpat, retest.S).findall(data1))
print("get page " + str(len(listurl)))
for i in range(0, len(listurl)):
time.sleep(7)
for j in range(0, len((listurl[i]))):
try:
url = listurl[i][j]
url = url.replace("amp;", "")
print("第" + str(i) + "i" + str(j) + "j次入队")
self.urlqueue.put(url)
self.urlqueue.task_done()
except urllib.error.URLError as e:
if hasattr(e, "code"):
print(e.code)
if hasattr(e, "reason"):
print(e.reason)
time.sleep(10)
except Exception as e:
print("excption:" + str(e))
time.sleep(1)
def getcontent(listurl, proxy):
i = 0
html1 = '''<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
<html xmlns="http://www.w3.org/1999/xhtml">
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
<title>微信文章页面</title>
</head>
<body>'''
fh = open("../1.html", "wb")
fh.close()
fh = open("../1.html", "ab")
for i in range(0, len(listurl)):
for j in range(0, len(listurl[i])):
try:
url = listurl[i][j]
url = url.replace("amp;", "")
data = use_proxy(proxy, url)
titlepat = "<title>(.*?)</title>"
contentpat = 'id="js_content">(.*?)id="js_sg_bar"'
title = retest.compile(titlepat).findall(data)
content = retest.compile(contentpat, retest.S).findall(data)
thistitle = "此次没有获取到"
thiscontent = "此次没有获取到"
if (title != []):
thistitle = title[0]
if (content != []):
thiscontent = content[0]
dataall = "<p>标题为:" + thistitle + "</p><p>内容为:" + thiscontent + "</p><br>"
fh.write(dataall.encode("utf-8"))
print("第" + str(i) + "个网页第" + str(j) + "次处理") #便于调试
except urllib.error.URLError as e:
if hasattr(e, "code"):
print(e.code)
if hasattr(e, "reason"):
print(e.reason)
except Exception as e:
print("exception:" + str(e))
time.sleep(1)
fh.close()
html2 = '''</body>
</html>
'''
fh = open("../1.html", "ab")
fh.write(html2.encode("utf-8"))
fh.close()
def run(self):
html1 = '''<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
<html xmlns="http://www.w3.org/1999/xhtml">
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
<title>微信文章页面</title>
</head>
<body>'''
fh = open("../2.html", "wb")
fh.write(html1.encode("utf-8"))
fh.close()
fh = open("../2.html", "ab")
i = 1
while (True):
try:
url = self.urlqueue.get()
data = use_proxy(self.proxy, url)
titlepat = "<title>(.*?)</title>"
contentpat = 'id="js_content">(.*?)id="js_sq_bar"'
title = retest.compile(titlepat).findall(data)
content = retest.compile(contentpat, retest.S).findall(data)
thistitle = "not this time"
thiscontent = "not this time"
if (title != []):
thistitle = title[0]
if (content != []):
thiscontent = content[0]
dataall = "<p>title:" + thistitle + "</p><p>content:" + thiscontent + "</p><br>"
fh.write(dataall.encode("utf-8"))
print("page" + str(i) + "...")
except urllib.error.URLError as e:
if hasattr(e, "code"):
print(e.code)
if hasattr(e, "reason"):
print(e.reason)
time.sleep(10)
except Exception as e:
print("exception:" + str(e))
time.sleep(1)
fh.close()
html2 = '''</body>
</html>
'''
fh = open("../2/html", "ab")
fh.write(html2.encode("utf-8"))
fh.close()
def getlink(url):
headers = ("user-agent","Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36")
opener=urllib.request.build_opener()
opener.addheaders=[headers]
urllib.request.install_opener(opener)
file=urllib.request.urlopen(url)
data=str(file.read())
pat='(https?://[^\s)";]+\.(\w|/)*)'
link=retest.compile(pat).findall(data)
link=list(set(link))
return link
def getcontent(url,page):
headers = ("user-agent", "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36")
opener=urllib.request.build_opener()
opener.addheaders=[headers]
urllib.request.install_opener(opener)
data=urllib.request.urlopen(url).read().decode("utf-8", errors='ignore')#这里转码有错误，先忽略吧
data=str(data)
# print(data)
# userpat='target="_blank" title="(.*?)">'
# < a class ="recmd-content" href="/article/121217166" target="_blank" onclick="_hmt.push(['_trackEvent','web-list-user','chick'])" > 咏哥走了，金大侠也走了，朋友圈又是一波接一波的轰炸。跑保险的借此说大病；做净水器的说喝水的重要性；做保健品的说产品疗效……我说，咏哥买不起保险还是安装不起净水器 < / a >
userpat="'web-list-user','chick'])\" >(.*?)</a>\""
# contentpat='<div class="content">(.*?)</div>'
# contentpat='<div class="content">(.*?)</div>'
# userlist=re.compile(userpat,re.S).findall(data)
userlist=retest.compile(userpat, retest.S).findall(data)
print(userlist)
def parse_one_page(html):
pattern = retest.compile(
'<dd>.*?board-index.*?>(\d+)</i>.*?<a.*?src="(.*?)">.*?name"><a' +
'.*?>(.*?)</a>.*?star">(.*?)</p>.*?releasetime">(.*?)</p>' +
'.*?integer">(.*?)</i>.*?fraction">(.*?)</i>.*?</dd>', retest.S)
items = retest.findall(pattern, html)
print(items)
for item in items:
yield {
'index': item[0],
'image': item[1],
'title': item[2].strip(),
'actor': item[3].strip()[3:] if len(item[3]) > 3 else '',
'time': item[4].strip()[5:] if len(item[4]) > 5 else '',
'score': item[5].strip() + item[6].strip()
}
def getlisturl(key, pagestart, pageend, proxy):
try:
page = pagestart
keycode = urllib.request.quote(key)
pagecode = urllib.request.quote("&page")
for page in range(pagestart, pageend + 1):
url = "http://weixin.sogou.com/weixin?type=2&query=" + keycode + pagecode + str(
page)
data1 = use_proxy(proxy, url)
listurlpat = '<div class="txt-box">.*?(http://.*?)"'
listurl.append(retest.compile(listurlpat, retest.S).findall(data1))
print("total" + str(len(listurl)))
return listurl
except urllib.error.URLError as e:
if hasattr(e, "code"):
print(e.code)
if hasattr(e, "reason"):
print(e.reason)
time.sleep(0)
except Exception as e:
print("exception:" + str(e))
time.sleep(1)
print(result2)
print("----------")
string = "apythonhellomypythonhispythonourpythonend"
pattern = ".python."
result = retest.match(pattern, string)
result2 = retest.match(pattern, string).span()
print(result)
print(result2)
print("----------")
string = "hellomypythonhispythonourpythonend"
pattern = ".python."
result = retest.match(pattern, string)
result2 = retest.search(pattern, string)
print(result)
print(result2)
print("----------")
string = "hellomypythonhispythonourpythonend"
pattern = retest.compile(".python.") #预编译
result = pattern.findall(string) #找出符合模式的所有结果
print(result)
result = retest.compile(".python.").findall(string)
print(result)
print("----------")
pattern = "python."
resultl = retest.sub(pattern, "php", string) #全部替换
result2 = retest.sub(pattern, "php", string, 2) #最多替换两次
headall.append(item)
opener.addheaders = headall
urllib.request.install_opener(opener)
#建立一个自定义函数craw(vid,comid),实现自动抓取对应评论网页并返回抓取数据
def craw(vid, comid):
url = "http://coral.qq.com/article/" + vid + "/comment?commentid=" + comid + "&reqnum=20"
data = urllib.request.urlopen(url).read().decode("utf-8")
return data
idpat = '"id":"(.*?)"'
userpat = '"nick":"(.*?)",'
conpat = '"content":"(.*?)",'
#第一层循环，代表抓取多少页，每一次外层循环抓取一页
for i in range(1, 10):
print("------------------------------------")
print("第" + str(i) + "页评论内容")
data = craw(vid, comid)
#第二层循环，根据抓取的结果提取并处理每条评论的信息，一页20条评论
for j in range(0, 20):
idlist = retest.compile(idpat, retest.S).findall(data)
userlist = retest.compile(userpat, retest.S).findall(data)
conlist = retest.compile(conpat, retest.S).findall(data)
print("用户名是 :" + eval('u"' + userlist[j] + '"'))
print("评论内容是:" + eval('u"' + conlist[j] + '"'))
print("\n")
#将comid改变为该页的最后一条评论id，实现不断自动加载
comid = idlist[19]
